_ registry / mcp streamable-http · checked 25h ago

Sema libraries

https://semahash.org

Registry code: d2d33dd1a137e0dc

api record

Read-only access to the Sema libraries published on semahash.org, with no install and no login. A library is a verified release of Pattern Cards: named mechanisms with invariants, failure modes and dependencies. Each card is named by the hash of its definition, so one reference always means one definition.

Every tool takes `library`. `bootstrap` is Sema's core vocabulary; `sema_library_search` lists the others.

endpoint
https://semahash.org/mcp
protocol
streamable-http ·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 Sema libraries live?
Yes — it answered the hub's last check (checked 25h ago). It answered 100% of checks over the last 30 days.
Is Sema libraries free to use?
Yes — the hub reached it with no key and no payment.
What tools does Sema libraries have?
7 tools: sema_tree, sema_search, sema_handshake, sema_graph_skeleton, sema_library_info, sema_resolve, sema_library_search.
Is Sema libraries 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 100%· all time 100%

latency
38ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ 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 7 tools
1 open 6 never probed 1 of 7 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.

  • sema_library_search open 25h ago

    Find the Sema libraries published on semahash.org. Each result gives the name to pass as `library` to the other tools, with the library's version, source repository, pattern count, semantic and catalog roots, license and page. `bootstrap` is Sema's core vocabulary. An empty query lists every library.

    mcp-tool

    {
      "type": "object",
      "title": "sema_library_searchArguments",
      "properties": {
        "query": {
          "type": "string",
          "title": "Query",
          "default": "",
          "maxLength": 200,
          "description": "Words that must all appear in the name, owner or repository"
        }
      }
    }
    arguments 13 lines
  • sema_tree unknown never probed

    Browse one library's patterns by layer and category. Without verbose, only handles are listed. Narrow a large library with `layer` or `category` before asking for glosses: a verbose tree too large for one result comes back without glosses, with a note.

    mcp-tool

    {
      "type": "object",
      "title": "sema_treeArguments",
      "required": [
        "library"
      ],
      "properties": {
        "layer": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 64
            },
            {
              "type": "null"
            }
          ],
          "title": "Layer",
          "default": null,
          "description": "Only this layer (Physics, Mind, Society, Infrastructure)"
        },
        "library": {
          "type": "string",
          "title": "Library",
          "maxLength": 64,
          "minLength": 1,
          "description": "Library name from sema_library_search, such as \"bootstrap\""
        },
        "verbose": {
          "type": "boolean",
          "title": "Verbose",
          "default": false,
          "description": "Add each pattern's gloss"
        },
        "category": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 64
            },
            {
              "type": "null"
            }
          ],
          "title": "Category",
          "default": null,
          "description": "Only this category; sema_tree lists them"
        }
      }
    }
    arguments 50 lines
  • sema_search unknown never probed

    Search one library's patterns by name, description or mechanism. Also search with the problem in front of you, for example "decide under uncertainty" or "find where a disagreement starts": patterns include protocols and checks that structure reasoning. Search matches words, not meaning, so try 2-3 phrasings with concrete nouns. The first three matches include search detail; later ones are summaries (`_summary: true`). Searching inside a layer or category ranks its closest patterns, weak matches included: use it alongside the unscoped search, not instead of it. Call `sema_resolve` for the complete Pattern Card.

    mcp-tool

    {
      "type": "object",
      "title": "sema_searchArguments",
      "required": [
        "library",
        "query"
      ],
      "properties": {
        "layer": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 64
            },
            {
              "type": "null"
            }
          ],
          "title": "Layer",
          "default": null,
          "description": "Only this layer (Physics, Mind, Society, Infrastructure)"
        },
        "limit": {
          "type": "integer",
          "title": "Limit",
          "default": 10,
          "maximum": 20,
          "minimum": 1,
          "description": "Maximum matches"
        },
        "query": {
          "type": "string",
          "title": "Query",
          "maxLength": 500,
          "minLength": 1,
          "description": "Concept, name or problem to search for"
        },
        "library": {
          "type": "string",
          "title": "Library",
          "maxLength": 64,
          "minLength": 1,
          "description": "Library name from sema_library_search, such as \"bootstrap\""
        },
        "category": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 64
            },
            {
              "type": "null"
            }
          ],
          "title": "Category",
          "default": null,
          "description": "Only this category; sema_tree lists them"
        }
      }
    }
    arguments 60 lines
  • sema_handshake unknown 25h ago

    Check that your definition is the one this library publishes. Compares content hashes: agreement means you hold the same definition, not that two agents will act alike. Without a hash, returns the canonical one (PROVIDE_HASH). With one: PROCEED, HALT (mismatch) or REQUIRE_FULL_HASH (a stub matched but strict needs the full hash). A hash inside `ref` counts as yours unless `your_hash` is given. Every known pattern or root reports its canonicalization. Pass the version used to compute your hash as `your_canonicalization`; do not substitute this library's version to make the comparison pass. Strict mode requires matching versions and reads an omitted version as 2. Cooperative mode warns when declared versions differ.

    mcp-tool

    {
      "type": "object",
      "title": "sema_handshakeArguments",
      "required": [
        "library",
        "ref"
      ],
      "properties": {
        "ref": {
          "type": "string",
          "title": "Ref",
          "maxLength": 300,
          "minLength": 1,
          "description": "Pattern reference (\"StateLock\", \"StateLock#c9c2\" or the full \"sema:StateLock#mh:SHA-256:<64 hex>\"), \"vocab\" for the semantic root or \"catalog\" for the catalog root"
        },
        "strict": {
          "type": "boolean",
          "title": "Strict",
          "default": false,
          "description": "Only a full 64-character hash can PROCEED"
        },
        "library": {
          "type": "string",
          "title": "Library",
          "maxLength": 64,
          "minLength": 1,
          "description": "Library name from sema_library_search, such as \"bootstrap\""
        },
        "your_hash": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 200
            },
            {
              "type": "null"
            }
          ],
          "title": "Your Hash",
          "default": null,
          "description": "Your hash: a stub or the full 64-character hash"
        },
        "your_scheme": {
          "anyOf": [
            {
              "type": "string",
              "maxLength": 100
            },
            {
              "type": "null"
            }
          ],
          "title": "Your Scheme",
          "default": null,
          "description": "Root scheme, required with your_hash for \"vocab\" or \"catalog\""
        },
        "your_canonicalization": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "title": "Your Canonicalization",
          "default": null,
          "description": "Canonicalization used to compute your hash (2 or 3), from your own workspace. Strict mode treats omission as 2 and halts on a difference."
        }
      }
    }
    arguments 71 lines
  • sema_graph_skeleton unknown 25h ago

    A short overview of one library: its regions, hubs and size.

    mcp-tool

    {
      "type": "object",
      "title": "sema_graph_skeletonArguments",
      "required": [
        "library"
      ],
      "properties": {
        "library": {
          "type": "string",
          "title": "Library",
          "maxLength": 64,
          "minLength": 1,
          "description": "Library name from sema_library_search, such as \"bootstrap\""
        }
      }
    }
    arguments 16 lines
  • sema_library_info unknown never probed

    One library's record and both of its aggregate roots. The semantic root commits to the set of definitions in the library; the catalog root commits to its exact handle-to-definition bindings. Compare them with `sema_handshake(library, ref="vocab" or "catalog", your_hash, your_scheme)`. Cite the library, version and root when you use it.

    mcp-tool

    {
      "type": "object",
      "title": "sema_library_infoArguments",
      "required": [
        "library"
      ],
      "properties": {
        "library": {
          "type": "string",
          "title": "Library",
          "maxLength": 64,
          "minLength": 1,
          "description": "Library name from sema_library_search, such as \"bootstrap\""
        }
      }
    }
    arguments 16 lines
  • sema_resolve unknown never probed

    The complete Pattern Card for one pattern, with its dependencies expanded. A reference that names a version (`Handle#stub` or a full hash) resolves only when that version is the one the library publishes; otherwise the error names the published reference. When the cards do not fit in one result, the nearest come first, whole, and `not_included` names the rest.

    mcp-tool

    {
      "type": "object",
      "title": "sema_resolveArguments",
      "required": [
        "library",
        "handle"
      ],
      "properties": {
        "depth": {
          "type": "integer",
          "title": "Depth",
          "default": 1,
          "maximum": 3,
          "minimum": 1,
          "description": "Dependency hops to expand"
        },
        "handle": {
          "type": "string",
          "title": "Handle",
          "maxLength": 200,
          "minLength": 1,
          "description": "Handle such as \"Stigmergy\", or a versioned reference such as \"Stigmergy#dd4f\""
        },
        "library": {
          "type": "string",
          "title": "Library",
          "maxLength": 64,
          "minLength": 1,
          "description": "Library name from sema_library_search, such as \"bootstrap\""
        }
      }
    }
    arguments 32 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 d2d33dd1a137e0dc.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/d2d33dd1a137e0dc/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/d2d33dd1a137e0dc/badge.svg)](https://brick.blue/agent/d2d33dd1a137e0dc?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.