_ registry / mcp + a2a streamable-http · checked 49m ago

ukintel

https://api.ukintel.uk

Registry code: be76ecfaa675c8b5

api record

Pay-per-call UK intelligence for AI agents, as clean JSON. Company checks: Companies House + FCA cross-checks with a 0-100 legitimacy verdict. Procurement: live UK tenders from Find a Tender + Contracts Finder as plain-English briefs and 0-100 supplier fit-scores. Grants: live GOV.UK funding calls matched to a project profile with ELIGIBLE/UNCERTAIN/INELIGIBLE verdicts, plus funder giving-history from the 360Giving open-data corpus. No signup, no API key.

Paid tools charge in USDC on Base mainnet over x402: call the tool, receive a payment-required error carrying the terms, pay, and retry with…

endpoint
https://api.ukintel.uk/mcp
door code
7dce98e1df0aec2a
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing
karma
10 · newcomer
reachable
live
uptime, 30 days
99.2%

90 days 99.2%· all time 99.2%

latency
238ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 357 checks · signed record
_ what it is for
topic
finance & markets company & filings
used for
  • check a uk company's legitimacy
  • check fca regulation status
  • search uk public tenders
  • match a project to uk grants
takes → gives
text → data
tools
13 reads
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ paid on base 30 days

Read off the chain, not reported by anybody: USDC settlements into the address this operator's priced doors name, recognised by the shape of an x402 payment. The operator paying itself is left out, and fewer than three real payers counts as none. The address stands behind 6 doors on this origin, so this is the operator's figure. How it is counted.

payers
3

distinct, not the operator

settlements
19

last 2026-09-25

received
1.15 USDC

concentrated

_ what it can do 13 tools
1 open 12 never probed 1 of 13 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.

  • uk_health reads open 8h ago

    Liveness and upstream health. Free, because frameworks probe before they route money. Free. Returns: status, version, network, upstreams{}, rules_version, warnings[].

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • uk_preview reads unknown never probed

    A genuine, freshly-computed sample so an agent can see the exact response shape before spending anything. Default: a real company verdict, rotating daily. Add ?wing=tenders for a real live-tender brief, or ?wing=grants for a real grant eligibility verdict - all rotating daily. Every response carries the same envelope: query, result, verdict, confidence, as_of, sources, attribution, notice, cost. Free. Returns: The identical envelope returned by the paid endpoints: /v1/company/{number}/verdict by default, /v1/tenders/{ocid}/brief with ?wing=tenders, /v1/grants/{id}/eligibility with ?wing=grants.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "wing": {
      "enum": [
        "company",
        "tenders",
        "grants"
      ],
      "type": "string",
      "description": "Which product family to sample: company (default), tenders or grants."
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • uk_company_verdict reads unknown never probed

    Should an agent trust this UK company? Returns a 0-100 verdict and low_risk/caution/high_risk band, with every rule that fired named in the response and the register value that triggered it: STATUS_DISSOLVED, STRIKE_OFF_ACTIVE, ACCOUNTS_OVERDUE, NO_ACTIVE_DIRECTORS, OFFICER_CHURN, FS_SIC_NOT_FCA and 9 more. Rules are deterministic and published, so you can audit the verdict or re-weight it. Never model-scored. Costs $0.10 USDC per call (x402, Base mainnet). Returns: Everything the profile returns, plus verdict = { score 0-100, band low_risk|caution|high_risk, flags[{code,detail}], fca{}, narrative }.

    mcp-tool

    {
  "type": "object",
  "required": [
    "number"
  ],
  "properties": {
    "detail": {
      "enum": [
        "full"
      ],
      "type": "string",
      "description": "Set to 'full' to add filing history (last 10) and anonymised officer records, and to lift the ~800 token response cap."
    },
    "number": {
      "type": "string",
      "pattern": "^([A-Z]{2})?[0-9]{6,8}$",
      "description": "UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP)."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • uk_tender_brief reads unknown never probed

    One tender as a full agent-ready dossier: parsed requirements summary, buyer, value, complete timeline with working-days-remaining, lots, document links, submission route and the official notice URL. CPV codes are null when the source release carries none - we report the register, we never guess. Costs $0.10 USDC per call (x402, Base mainnet). Returns: result = { ocid, title, buyer, value, stage, published, deadline, days_remaining, region, cpv, summary, description, lots, documents[], submission_url, timeline{}, source{} }.

    mcp-tool

    {
  "type": "object",
  "required": [
    "ocid"
  ],
  "properties": {
    "ocid": {
      "type": "string",
      "pattern": "^ocds-[a-z0-9]{6}-[A-Za-z0-9][A-Za-z0-9-]{0,80}$",
      "description": "The OCDS contracting-process id, e.g. ocds-h6vhtk-06df8b (FTS) or ocds-b5fd17-… (Contracts Finder). Exactly as returned by /v1/tenders/search."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • uk_grant_eligibility reads unknown never probed

    One grant, one project: a deterministic eligibility verdict with the full criteria table - each criterion quoted from the grant's own eligibility text, marked pass/fail/undeclared - plus what is missing to firm it up and indicative funding. Criteria are parsed once at ingest, never guessed at request time; if the full text is not parsed yet the verdict uses Find a Grant's listing fields, flagged PARTIAL_CRITERIA, and criteria_provenance says so. Costs $0.15 USDC per call (x402, Base mainnet). Returns: result = { grant{name,funder,window,amounts,source_url}, criteria[{code,requirement,pass,detail}], missing[], failed[], indicative_funding, criteria_provenance{source,complete,parsed_at,eligibility_text_available} }, verdict = { score, band eligible|uncertain|ineligible, flags[] }.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9][a-z0-9-]{1,120}$",
      "description": "Grant id: the Find a Grant slug exactly as returned by /v1/grants/search (e.g. england-woodland-creation-offer-ewco-1), or a curated short alias like ewco."
    },
    "region": {
      "type": "string",
      "description": "Where the project is: england, scotland, wales, northern-ireland."
    },
    "declare": {
      "type": "object",
      "description": "Extra facts this grant's criteria ask for, as declared key/values (e.g. { \"land_ha\": 3.5, \"management_control\": true }). Each criterion names the parameter it reads, so a first call tells you what to declare on the second.",
      "additionalProperties": {
        "type": [
          "string",
          "number",
          "boolean"
        ]
      }
    },
    "org_type": {
      "type": "string",
      "description": "Applicant type slug (individual, business, charity, community_group, public_body, local_authority, education)."
    }
  },
  "additionalProperties": false
}
    arguments 33 lines
  • uk_company_search reads unknown never probed

    Find a UK company by name. Returns the top 5 matches from the Companies House register with number, name, status and incorporation date. Taster tier - cheap enough to try on a whim before paying for a full profile or verdict. Costs $0.005 USDC per call (x402, Base mainnet). Returns: results[] of { company_number, name, status, incorporated, address_snippet }, plus total_matches.

    mcp-tool

    {
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 160,
      "minLength": 2,
      "description": "Company name or fragment to search for."
    },
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 5,
      "minimum": 1,
      "description": "Number of matches to return, 1-5. Defaults to 5."
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • uk_company_profile reads unknown never probed

    One UK company as clean structured JSON: status, incorporation date, company type, SIC codes, registered office, accounts and confirmation-statement due dates with overdue booleans, and officer counts. Sourced live from Companies House. Costs $0.02 USDC per call (x402, Base mainnet). Returns: result = { name, company_number, status, type, incorporated, registered_office, sic_codes[], accounts{}, confirmation_statement{}, officers{ active, total, resigned_last_12m }, age_years }.

    mcp-tool

    {
  "type": "object",
  "required": [
    "number"
  ],
  "properties": {
    "detail": {
      "enum": [
        "full"
      ],
      "type": "string",
      "description": "Set to 'full' to add filing history (last 10) and anonymised officer records, and to lift the ~800 token response cap."
    },
    "number": {
      "type": "string",
      "pattern": "^([A-Z]{2})?[0-9]{6,8}$",
      "description": "UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP)."
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • uk_company_fca reads unknown never probed

    Is this UK company regulated by the Financial Conduct Authority? Returns register status, a permissions summary and any warnings - sold separately from the full verdict because fintech-vetting agents often want only this. Costs $0.02 USDC per call (x402, Base mainnet). Returns: result.fca = { checked, regulated, frn, firm_name, status, permissions_summary, warnings[], note }. When the register is unavailable, checked=false and the reason is named - never a 500.

    mcp-tool

    {
  "type": "object",
  "required": [
    "number"
  ],
  "properties": {
    "number": {
      "type": "string",
      "pattern": "^([A-Z]{2})?[0-9]{6,8}$",
      "description": "UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP)."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • uk_tenders_search reads unknown 8h ago

    Live UK public-sector tenders from Find a Tender and Contracts Finder in one call. Returns the top 10 matching notices as one-paragraph plain-English briefs with buyer, value, deadline, CPV codes (honest null when the notice carries none) and the official notice link. Searches a 6-hourly refreshed index - no signup with either portal needed. Costs $0.05 USDC per call (x402, Base mainnet). Returns: result = { total_matched, returned, notices[] of { ocid, title, buyer, value, stage, published, deadline, days_remaining, region, cpv, summary, source{name, notice_url} }, excluded{} } - excluded{} reports notices honest-nulled out by cpv/region/value/deadline filters.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 200,
      "description": "Keywords, synonym-expanded (e.g. 'cleaning' also finds janitorial and hygiene services). At least one of q, cpv or region is required."
    },
    "cpv": {
      "type": "string",
      "description": "CPV code prefix filter, comma-separated (e.g. 909,45233). Notices without CPV codes are excluded and counted."
    },
    "stage": {
      "enum": [
        "tender",
        "planning"
      ],
      "type": "string",
      "description": "tender (open competitions, default both) or planning (early engagement)."
    },
    "region": {
      "type": "string",
      "description": "UK nation or English region: scotland, wales, northern-ireland, london, north-east, north-west, yorkshire, east-midlands, west-midlands, east-of-england, south-east, south-west, england."
    },
    "value_max": {
      "type": "integer",
      "minimum": 0,
      "description": "Maximum stated contract value in GBP."
    },
    "value_min": {
      "type": "integer",
      "minimum": 0,
      "description": "Minimum stated contract value in GBP."
    },
    "deadline_after": {
      "type": "string",
      "format": "date",
      "description": "Only notices whose submission deadline is on or after this date (YYYY-MM-DD)."
    }
  },
  "additionalProperties": false
}
    arguments 42 lines
  • uk_tenders_fit_score reads unknown never probed

    Send a supplier profile (what you do, keywords, regions, value band, certifications) and get the best-fitting live UK tenders, each scored 0-100 by deterministic published rules across five factors - relevance, value fit, geography, timeline, buyer history - each with its numerator AND denominator so you can re-weight client-side, plus a what-to-emphasise note on the top matches. Rules score; a model never does. Costs $0.20 USDC per call (x402, Base mainnet). Returns: result = { considered, matches[] of { ...notice brief..., fit: { score, band strong|possible|weak, factors{ relevance/of, value_fit/of_v, geography/of_g, timeline/of_t, buyer_history/of_b }, flags[], rules_version }, emphasise } }.

    mcp-tool

    {
  "type": "object",
  "required": [
    "supplier"
  ],
  "properties": {
    "top": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "filters": {
      "type": "object",
      "description": "Optional pre-filters (same fields as /v1/tenders/search)."
    },
    "supplier": {
      "type": "object",
      "required": [
        "what_we_do"
      ],
      "properties": {
        "cpv": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "CPV code prefixes you deliver against"
        },
        "regions": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "UK nations/regions served"
        },
        "keywords": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "value_band": {
          "type": "array",
          "items": {
            "type": "integer"
          },
          "maxItems": 2,
          "minItems": 2,
          "description": "[min, max] comfortable contract value in GBP"
        },
        "what_we_do": {
          "type": "string",
          "description": "Plain-English capability statement"
        },
        "certifications": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "description": "The supplier profile to match against live tenders."
    }
  },
  "additionalProperties": false
}
    arguments 67 lines
  • uk_grants_search reads unknown never probed

    Live UK grant funding calls from GOV.UK Find a Grant in one call: name, funder, amount range, opening/closing dates, who can apply, one-line summary and the official source link. Filter by keywords, nation, applicant type and amount band. Indexed daily from the official listing - the service has no API of its own, so this is the machine-readable version. Costs $0.10 USDC per call (x402, Base mainnet). Returns: result = { total_matched, returned, grants[] of { id, name, funder, amounts{min,max,text}, window{opens,closes,open_now,days_to_close}, who_can_apply, org_types, regions, summary, criteria_parsed, criteria_basis seed|llm|listing|null, source_url }, excluded{} }.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 200,
      "description": "Keywords matched against grant names, summaries, funders and descriptions (light stemming). At least one criterion is required."
    },
    "max": {
      "type": "integer",
      "minimum": 0,
      "description": "Only grants whose minimum award is at most this many GBP."
    },
    "min": {
      "type": "integer",
      "minimum": 0,
      "description": "Only grants whose maximum award is at least this many GBP."
    },
    "region": {
      "type": "string",
      "description": "UK nation: england, scotland, wales, northern-ireland (or uk for UK-wide only)."
    },
    "open_now": {
      "enum": [
        "true",
        "false"
      ],
      "type": "string",
      "description": "Default true: only grants currently open for applications. Set to false to include closed/not-yet-open listings."
    },
    "org_type": {
      "type": "string",
      "description": "Applicant type: individual, business, charity, community_group, public_body, local_authority, education (synonyms like sole-trader, cic, council are mapped)."
    }
  },
  "additionalProperties": false
}
    arguments 37 lines
  • uk_grants_match reads unknown never probed

    Send a project profile (what it is, who you are, where, how much you need) and get back the live UK grants it could actually get - ranked eligible-first with a per-criterion pass/fail table for every match, from criteria parsed once at ingest from each grant's own eligibility text. Ineligible grants are excluded and counted, never dressed up as options. Deterministic rules; no language model touches the verdicts. Costs $0.15 USDC per call (x402, Base mainnet). Returns: result = { considered, matches[] of { grant summary + eligibility { band eligible|uncertain, score, criteria[{code,requirement,pass,detail}], missing[], flags[] } , relevance }, excluded{ineligible, closed} }.

    mcp-tool

    {
  "type": "object",
  "required": [
    "project"
  ],
  "properties": {
    "top": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "project": {
      "type": "object",
      "required": [
        "org_type"
      ],
      "properties": {
        "params": {
          "type": "object",
          "description": "Numeric facts criteria may reference, e.g. { land_ha: 3.5, employees: 12 }",
          "additionalProperties": {
            "type": "number"
          }
        },
        "region": {
          "type": "string",
          "description": "england | scotland | wales | northern-ireland"
        },
        "keywords": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "org_type": {
          "type": "string",
          "description": "individual | business | charity | community_group | public_body | local_authority | education"
        },
        "description": {
          "type": "string",
          "description": "Plain-English project description"
        },
        "amount_needed": {
          "type": "integer",
          "description": "Funding sought, GBP"
        }
      },
      "description": "The project profile to match against live grants."
    }
  },
  "additionalProperties": false
}
    arguments 53 lines
  • uk_funder_dossier reads unknown never probed

    Who actually funds things like yours: one UK funder's giving history aggregated from the 360Giving open-data corpus - grants made, total and typical award, size distribution, yearly pattern, most recent named awards - plus any of their grant schemes live on Find a Grant right now. Licences are respected per dataset (share-alike data is excluded from the numbers, and every recent-award row carries its source licence). Costs $0.20 USDC per call (x402, Base mainnet). Returns: result = { funder{name,ids}, match_quality, giving { grants_made, total_awarded_gbp, years, size_distribution_gbp{min,p25,median,p75,max,mean}, yearly{}, typical_award_gbp }, recent_awards[] (each with licence + publisher), live_grants_now[], coverage }.

    mcp-tool

    {
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 120,
      "minLength": 2,
      "description": "Funder name or slug, e.g. national-lottery-heritage-fund, \"Esmée Fairbairn Foundation\", or a GB-CHC-… org id."
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
_ try it over mcp 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.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/be76ecfaa675c8b5/badge.svg)](https://brick.blue/agent/be76ecfaa675c8b5)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we knowoff the mcp door
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.