_ registry / mcp http-sse · checked 2h ago

paymentslaw

https://mcp.paymentslaw.eu

Registry code: f9a2461b17a0248f

api record

EU Payments Law (paymentslaw.eu): EU payments legislation at provision level, 63 curated instruments. Every provision carries its source, version and legal status, and a citation that opens on the official record. When the corpus cannot answer, it says so.

It serves source-based EU payments research: strong customer authentication (SCA), dynamic linking, open banking, payment liability and safeguarding. Held instruments include PSD2, RTS-SCA, PSD3/PSR and DORA; list_instruments gives the actual coverage and status.

endpoint
https://mcp.paymentslaw.eu/mcp/v1
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is paymentslaw live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is paymentslaw free to use?
Yes — the hub reached it with no key and no payment.
What tools does paymentslaw have?
14 tools: get_defined_term, get_instrument, get_provision, get_source_notes, list_provisions, search_legislation, search, compare_versions, ….
Is paymentslaw safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 99.7%· all time 99.7%

latency
327ms

last good check

priced tools
0

of 14 tools

_ answered our checks, 90 days 600 checks · signed record
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
government & legal legal
used for
  • search eu payments legislation
  • read a provision of psd2 or psr
  • compare legislative versions
  • resolve an eu legal citation
  • look up a defined legal term
takes → gives
text → text, data
tools
14 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 14 tools
3 open 11 never probed 3 of 14 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_instruments reads open 6h ago

    Use this to discover which EU instruments are held before a coverage question, or find their registry ids and legal status. Paginated, filterable by status, category, core/supplementary, and by whether an instrument was in force on a given date. For corpus-coverage questions, filter by category here, enumerate each instrument with list_provisions, then open what you need with get_provision.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991
        },
        {
          "type": "null"
        }
      ]
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ]
    },
    "status": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Legal status at the release, e.g. \"in_force\"."
    },
    "is_core": {
      "type": [
        "boolean",
        "null"
      ]
    },
    "category": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ]
    },
    "in_force_on_date": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 32
        },
        {
          "type": "null"
        }
      ],
      "description": "ISO date; keeps instruments in force on that date."
    }
  }
}
    arguments 71 lines
  • search_defined_terms reads open 6h ago

    Use this to find which EU instruments define a legal term, such as payment transaction or payment account, and where their definitions differ. For definition wording use get_defined_term. A listing: term, definers and divergence flags, with no definition text. Matching is over the term itself, never the definition body. Divergence is judged on the RESOLVED text as well as the verbatim one, because several instruments defining a term by pointing at the same root agree, however differently their pointers read. Pass only_divergent to find where the corpus does not agree with itself.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991
        },
        {
          "type": "null"
        }
      ]
    },
    "query": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 256
        },
        {
          "type": "null"
        }
      ],
      "description": "Term text to match. Matching is over the TERM only, never the definition body. Omit for the full alphabetical listing of every term the corpus defines."
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ]
    },
    "instrument": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Keep only terms defined in this instrument, e.g. \"psd-2\"."
    },
    "only_divergent": {
      "type": [
        "boolean",
        "null"
      ],
      "description": "Keep only terms whose definers disagree — on the resolved text, the verbatim text, or both."
    }
  }
}
    arguments 62 lines
  • get_orientation reads open 6h ago

    Use this for a starting reading order in EU payments legislation when a relevant curated pathway exists. For other subjects use search_legislation. Curated reading pathways into the corpus for a stated audience: ordered waypoints with cite anchors every other tool can open, related defined terms and known pitfalls. The prose is editorial and labelled as such — it maps the reading order, never legal weight. Omit the pathway argument for the catalogue; an unknown id is refused with the catalogue, nothing substituted. Catalogue entries and pathway waypoints paginate whole: follow pagination.next_cursor with the same pathway and limit until complete.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 100,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "description": "Maximum catalogue entries or pathway waypoints per page; whole-item byte bounds may return fewer."
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ],
      "description": "pagination.next_cursor from this tool; repeat the same pathway and limit."
    },
    "pathway": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Pathway id from the catalogue. Omit for the catalogue."
    }
  }
}
    arguments 45 lines
  • get_defined_term reads unknown 16h ago

    Use this to read and compare the held legislative definitions of a term, such as payment transaction in PSD2 and PSR. These are source definitions, not a general dictionary or a legal opinion. Every definition verbatim and resolved, clustered by what the text actually says, with the chronological and concurrent views and word-level comparisons between them. Resolution follows the CITED version, never legislative succession: a definition citing a repealed act resolves to that act and is labelled repealed, not silently replaced by its successor's wording. A term the corpus does not define is refused with suggestions — nothing is substituted. references_in gives the reverse edges: which definitions lean on this one.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "term"
  ],
  "properties": {
    "term": {
      "type": "string",
      "maxLength": 256,
      "description": "The defined term, as written in the legislation (\"payment account\"). Matched exactly after normalisation; a term the corpus does not define is refused with suggestions, never answered with a neighbouring one."
    },
    "view": {
      "anyOf": [
        {
          "enum": [
            "resolved",
            "verbatim"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Which text clusters and comparisons run on. \"resolved\" (default) follows each definition's pointers to its root; \"verbatim\" uses the text as each instrument prints it."
    },
    "on_date": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 32
        },
        {
          "type": "null"
        }
      ],
      "description": "ISO date. Adds operative_on_date and temporal_state_on_date per definer, and makes the concurrent view that date's rather than the release's."
    },
    "comparison": {
      "anyOf": [
        {
          "anyOf": [
            {
              "type": "string",
              "const": "adjacent"
            },
            {
              "type": "object",
              "required": [
                "baseline"
              ],
              "properties": {
                "baseline": {
                  "type": "string",
                  "pattern": "^[0-9a-f]+$",
                  "maxLength": 64
                }
              }
            },
            {
              "type": "object",
              "required": [
                "pair"
              ],
              "properties": {
                "pair": {
                  "type": "array",
                  "items": false,
                  "maxItems": 2,
                  "minItems": 2,
                  "prefixItems": [
                    {
                      "type": "string",
                      "pattern": "^[A-Za-z0-9 ()-]+$",
                      "maxLength": 128
                    },
                    {
                      "type": "string",
                      "pattern": "^[A-Za-z0-9 ()-]+$",
                      "maxLength": 128
                    }
                  ]
                }
              }
            },
            {
              "type": "object",
              "required": [
                "concurrent_pairs"
              ],
              "properties": {
                "concurrent_pairs": {
                  "type": "object",
                  "properties": {
                    "cursor": {
                      "anyOf": [
                        {
                          "type": "string",
                          "pattern": "^[A-Za-z0-9_-]+$",
                          "maxLength": 512
                        },
                        {
                          "type": "null"
                        }
                      ]
                    }
                  }
                }
              }
            }
          ]
        },
        {
          "type": "null"
        }
      ],
      "description": "Which comparisons to compute. \"adjacent\" (default) compares consecutive distinct clusters in chronological order; {baseline: cluster_id} compares one cluster against every other; {pair: [cite, cite]} compares two named definitions; {concurrent_pairs: {}} compares every pair that was in force at once."
    },
    "instrument": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Narrow the definitions listed to one definer. The clusters, views and comparisons stay corpus-wide: what the term means elsewhere does not change because you asked about one instrument."
    }
  }
}
    arguments 134 lines
  • get_instrument reads unknown 16h ago

    Use this to check an EU instrument's recorded legal status, source version, dates and amendments, including whether a held PSR or PSD3 text is a proposal, a Council compromise text or the act published in the Official Journal. Metadata, dates, lifecycle and application events, and curated relationships. Each relationship names the operative amending or repealing article where curated (openable with get_provision) and the counterpart's legal status at the release. An operative_cite can arrive without an operative_locator: the article is real but the served text has dropped it, and operative_locator_unavailable says so. An amender outside the corpus is named under source_external, whose via_article carries its article. No article index — use list_provisions. Pass on_date for the multi-axis applicability record on that date.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "instrument_id"
  ],
  "properties": {
    "on_date": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 32
        },
        {
          "type": "null"
        }
      ],
      "description": "ISO date; returns the full applicability record."
    },
    "instrument_id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 64
    }
  }
}
    arguments 26 lines
  • get_provision reads unknown 16h ago

    Use this to read or quote an EU legislative provision, such as PSD2 Article 97 or RTS-SCA Article 5. Returns the source text of an article, annex or recital as markdown (a sub- or superscript with no Unicode form as inline <sub>/<sup>), with its cite anchor, provenance and text-state disclosure. Large provisions paginate by structural block — never truncated silently. version_id is optional: the service serves one text per instrument, and a pinned version id is refused with the URL where it is published. include_correspondences adds the cross-instrument article equivalences — what a PSR article is amended from, or which PSR articles carry a PSD2 article's obligation — each openable by a second call.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "instrument_id",
    "locator"
  ],
  "properties": {
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ],
      "description": "Continue a paginated provision. Bound to the release."
    },
    "locator": {
      "type": "object",
      "required": [
        "kind"
      ],
      "properties": {
        "kind": {
          "enum": [
            "article",
            "annex",
            "recital"
          ],
          "type": "string",
          "description": "Which kind of provision the locator names."
        },
        "annex": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 32
            },
            {
              "type": "null"
            }
          ],
          "description": "Annex number, roman or arabic (\"I\", \"1\"); omit for an instrument whose single annex is unnumbered."
        },
        "point": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 32
            },
            {
              "type": "null"
            }
          ],
          "description": "Lettered point within the paragraph, e.g. \"b\"."
        },
        "article": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 32
            },
            {
              "type": "null"
            }
          ],
          "description": "Article number as printed: \"97\", \"45a\", \"69-a\"."
        },
        "recital": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 32
            },
            {
              "type": "null"
            }
          ],
          "description": "Recital number, e.g. \"95\"."
        },
        "subpoint": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 32
            },
            {
              "type": "null"
            }
          ],
          "description": "Sub-point within the point."
        },
        "paragraph": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 32
            },
            {
              "type": "null"
            }
          ],
          "description": "Numbered paragraph within the article, e.g. \"2\"."
        }
      }
    },
    "on_date": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 32
        },
        {
          "type": "null"
        }
      ],
      "description": "ISO date; returns the provision-level applicability view."
    },
    "version_id": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9]+(?:-[A-Za-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Omit, or pass \"current\", for the served text. A pinned version id returns version_not_served with the URL where that text is published."
    },
    "instrument_id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 64,
      "description": "Registry id of the instrument, e.g. \"psd-2\"."
    },
    "include_correspondences": {
      "type": [
        "boolean",
        "null"
      ],
      "description": "Off by default. When true, an article carries `correspondences[]`: the cross-instrument article equivalences the corpus publishes — which PSD2 article a PSR article is amended from, and, from the other side, which PSR articles carry a PSD2 article's obligation. Each entry names the counterpart's own `get_provision` locator, version and cite anchor, so it opens with a second call. The relationship vocabulary is the analysis layer's own — `amended_from`, `supersedes` — plus the mechanical inverses of the reverse view, `amended_into` and `superseded_by`. An annex or a recital carries an empty list: correspondences are article-level: a request narrowed to a paragraph or a point still receives the whole article's mappings, and says so in a warning. `null` means the release predates the mapping table, which is not the same as an article having none. Where the corpus records a mapping this service will not serve — a correlation-table entry numbered against a superseded draft, or a counterpart absent from the served text — the list omits it and a `correspondence_withheld` warning names the instrument and the reason, so an empty or short list is never silently under-claimed."
    }
  }
}
    arguments 150 lines
  • get_source_notes reads unknown 12h ago

    Use this to read the original legislative footnotes and source-note bodies for a held instrument, including preamble and annex notes. Omit note_key for the paginated inventory; supply an exact returned key to retrieve one. Keys retain source scope because printed markers may repeat. This tool does not infer ownership by a provision. Historical versions return an explicit version_not_served link.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "instrument_id"
  ],
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 100,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "description": "Notes per page, default 10; complete bodies are never truncated."
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ],
      "description": "Continue with the same arguments; bound to this corpus release."
    },
    "note_key": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9*._-]+$",
          "maxLength": 128,
          "minLength": 1
        },
        {
          "type": "null"
        }
      ],
      "description": "Exact key returned by this tool. Omit to list notes. Printed markers may be reused and are not necessarily unique keys."
    },
    "version_id": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9]+(?:-[A-Za-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Omit or use current for the served version; pinned versions return an explicit version_not_served link."
    },
    "instrument_id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 64,
      "description": "Registry instrument id."
    }
  }
}
    arguments 68 lines
  • list_provisions reads unknown 12h ago

    Use this to browse an EU instrument's article, annex or recital index, or enumerate its topic-tagged provisions for a coverage question. Metadata only: each item carries the exact locator get_provision accepts. Articles and annexes by default; pass kind=recital for recitals.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "instrument_id"
  ],
  "properties": {
    "kind": {
      "anyOf": [
        {
          "enum": [
            "article",
            "annex",
            "recital"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ]
    },
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991
        },
        {
          "type": "null"
        }
      ]
    },
    "topic": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ]
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ]
    },
    "chapter": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 256
        },
        {
          "type": "null"
        }
      ]
    },
    "instrument_id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 64
    }
  }
}
    arguments 75 lines
  • search_legislation reads unknown 2h ago

    Use this to find EU legislative provisions on payment-services questions: strong customer authentication (SCA), dynamic linking, open banking, safeguarding and payment liability. The held corpus includes PSD2, RTS-SCA, PSD3/PSR and DORA. For exact wording use get_provision; for defined-term wording use get_defined_term. This searches held legislation, not national law or regulator guidance. Full-text search across articles, annexes and recitals, ranked in that order of authority. Every hit carries the exact locator get_provision accepts, its cite anchor, the matched passage and why it matched. A citation-shaped query resolves through the citation grammar first; instrument acronyms become ranking hints; initialisms of the corpus's defined terms are expanded. Absence of a result is not evidence that no relevant law exists. The matched passage is a snippet of at most 320 characters, not the provision: open the hit with get_provision before citing it, and echo the cite it serves. topic narrows these hits rather than widening them: a topic-tagged provision whose words the query misses is never reached, so a page of hits is not a sweep. For coverage questions ('everything on X', 'which instruments deal with Y') pick the instruments with list_instruments by category, enumerate each with list_provisions filtered by topic, then open them with get_provision.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "kind": {
      "anyOf": [
        {
          "enum": [
            "article",
            "annex",
            "recital"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Restrict to one source type. Articles, annexes and recitals are all searched by default, ranked in that order of authority."
    },
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991
        },
        {
          "type": "null"
        }
      ]
    },
    "query": {
      "type": "string",
      "description": "EU legislative search terms, e.g. \"strong customer authentication\", \"dynamic linking\", \"safeguarding\" or \"DORA ICT risk\". Use words expected in the legal text, not an entire advice request. Quoted phrases are honoured; AND, OR and NOT are the only operators. A citation-shaped query (\"Article 97(1) PSD2\") is resolved through the citation grammar first."
    },
    "topic": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Keep only provisions carrying this topic."
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ]
    },
    "instrument_id": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Restrict to one instrument, e.g. \"rts-sca\"."
    },
    "in_force_on_date": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 32
        },
        {
          "type": "null"
        }
      ],
      "description": "ISO date; keeps hits from instruments in force on that date, on the same semantics list_instruments uses."
    }
  }
}
    arguments 90 lines
  • search reads unknown 2h ago

    Use this to find EU payments legislation on topics such as SCA, open banking and safeguarding in the held PSD2, RTS-SCA, PSD3/PSR and related instruments. Simple search returning the top hits as {id, title, url}, where id is the cite anchor fetch accepts. For filters, snippets, scores and paging use search_legislation, which returns more.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "EU payments legislative terms or citation, e.g. \"strong customer authentication\", \"safeguarding\" or \"Article 97 PSD2\"."
    }
  }
}
    arguments 13 lines
  • compare_versions reads unknown 12h ago

    Use this to compare an article between the Commission proposal and the Council compromise text of PSR or PSD3, within the same instrument. Serves the word-level comparison the build published: a pair is servable if and only if a diff artefact exists for it — the PSR and PSD3 proposal↔compromise pairs and nothing else. Every other pair is refused, including any with a text published in the Official Journal; for every consolidated instrument's pinned as-adopted text the refusal carries the URL where that text is published. This service never recomputes a comparison. Pairs match in either direction, and a reversed request is the same artefact with the ops inverted. `changes` reads that artefact structurally — paragraphs added or deleted, figures and durations moved, a heading rewritten — for a caller that needs what KIND of change this was without parsing the word-level ops. It is scoped to the article, not to the page of ops, and locates each entry no more precisely than the served text allows.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "instrument_id",
    "from_version_id",
    "to_version_id"
  ],
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991
        },
        {
          "type": "null"
        }
      ]
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ]
    },
    "to_locator": {
      "anyOf": [
        {
          "type": "object",
          "required": [
            "kind"
          ],
          "properties": {
            "kind": {
              "enum": [
                "article",
                "annex",
                "recital"
              ],
              "type": "string",
              "description": "Which kind of provision the locator names."
            },
            "annex": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Annex number, roman or arabic (\"I\", \"1\"); omit for an instrument whose single annex is unnumbered."
            },
            "point": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Lettered point within the paragraph, e.g. \"b\"."
            },
            "article": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Article number as printed: \"97\", \"45a\", \"69-a\"."
            },
            "recital": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Recital number, e.g. \"95\"."
            },
            "subpoint": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Sub-point within the point."
            },
            "paragraph": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Numbered paragraph within the article, e.g. \"2\"."
            }
          }
        },
        {
          "type": "null"
        }
      ],
      "description": "The article on the to side."
    },
    "from_locator": {
      "anyOf": [
        {
          "type": "object",
          "required": [
            "kind"
          ],
          "properties": {
            "kind": {
              "enum": [
                "article",
                "annex",
                "recital"
              ],
              "type": "string",
              "description": "Which kind of provision the locator names."
            },
            "annex": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Annex number, roman or arabic (\"I\", \"1\"); omit for an instrument whose single annex is unnumbered."
            },
            "point": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Lettered point within the paragraph, e.g. \"b\"."
            },
            "article": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Article number as printed: \"97\", \"45a\", \"69-a\"."
            },
            "recital": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Recital number, e.g. \"95\"."
            },
            "subpoint": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Sub-point within the point."
            },
            "paragraph": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ],
              "description": "Numbered paragraph within the article, e.g. \"2\"."
            }
          }
        },
        {
          "type": "null"
        }
      ],
      "description": "The article on the from side. Alignment is identity on the article number, so naming either side names both."
    },
    "instrument_id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 64,
      "description": "Registry id of the instrument, e.g. \"psr\"."
    },
    "to_version_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9]+(?:-[A-Za-z0-9]+)*$",
      "maxLength": 64,
      "description": "Version id the other side."
    },
    "from_version_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9]+(?:-[A-Za-z0-9]+)*$",
      "maxLength": 64,
      "description": "Version id one side of the pair."
    }
  }
}
    arguments 247 lines
  • fetch reads unknown 9h ago

    Use this to open and cite an EU legislative provision found by search. Simple retrieval of one provision's text by its cite anchor id (e.g. "psd-2 Art 97"), with citation metadata. A provision longer than the response ceiling arrives in part, with metadata.complete false and a metadata.next_cursor that get_provision continues. Accepts only ids this service minted — free-text citations belong to resolve_citation. get_provision returns more: paging, applicability and typed warnings.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "An id from search, or a cite anchor such as \"psd-2 Art 97\" or \"psd-2 Recital 12\", or an instrument id such as \"psd-2\". An optional version qualifier, e.g. \"psr (com-2023-367) Art 105\", retains its edition and refuses unserved text."
    }
  }
}
    arguments 13 lines
  • list_version_changes reads unknown 9h ago

    Use this to browse which articles changed between the Commission proposal and the Council compromise text of PSR or PSD3; no comparison with a text published in the Official Journal is held. For one article's wording changes use compare_versions. Across those two texts, lists every aligned article with its classification, filterable by status, materiality and article range. The editorial materiality markers travel on every response whatever the filters, because they exist precisely where the mechanical classification does not show what matters — a re-scoped defined term changes articles whose text did not change at all. Classifications are mechanical, and the response says on what basis.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "instrument_id"
  ],
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991
        },
        {
          "type": "null"
        }
      ]
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ]
    },
    "status": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "One of the classification statuses, e.g. \"amended_substantial\"."
    },
    "articles": {
      "anyOf": [
        {
          "type": "object",
          "properties": {
            "to": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ]
            },
            "from": {
              "anyOf": [
                {
                  "type": "string",
                  "maxLength": 32
                },
                {
                  "type": "null"
                }
              ]
            }
          }
        },
        {
          "type": "null"
        }
      ],
      "description": "Article-number range, in legal order."
    },
    "instrument_id": {
      "type": "string",
      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
      "maxLength": 64
    },
    "material_only": {
      "type": [
        "boolean",
        "null"
      ],
      "description": "Keep only articles carrying an editorial materiality marker."
    },
    "to_version_id": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9]+(?:-[A-Za-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ]
    },
    "from_version_id": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9]+(?:-[A-Za-z0-9]+)*$",
          "maxLength": 64
        },
        {
          "type": "null"
        }
      ],
      "description": "Optional; where given, must name the published pair."
    }
  }
}
    arguments 117 lines
  • resolve_citation reads unknown 9h ago

    Use this to resolve a written EU legal citation, such as Article 97(1) PSD2, into an instrument and provision locator. For a topic rather than a citation, use search_legislation. Ranked candidates with ambiguity flagged and confidence stated: exact (instrument certain, provision found), strong (instrument certain, provision not verified or not named) or ambiguous (more than one reading). A citation of an instrument this corpus does not hold is named, with its CELEX and ELI, rather than guessed at.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "citation"
  ],
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 9007199254740991,
          "minimum": -9007199254740991
        },
        {
          "type": "null"
        }
      ]
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9_-]+$",
          "maxLength": 512
        },
        {
          "type": "null"
        }
      ]
    },
    "citation": {
      "type": "string",
      "description": "A citation in any form a reader would write: \"Article 97(1) PSD2\", \"Art. 5a of Regulation (EU) No 910/2014\", a CELEX number, an ELI path, or a bare acronym."
    }
  }
}
    arguments 37 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id f9a2461b17a0248f.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f9a2461b17a0248f/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/f9a2461b17a0248f/badge.svg)](https://brick.blue/agent/f9a2461b17a0248f?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.