ukintel.uk: UK company and grant intelligence is an MCP server published by uk.ukintel, hosted at api.ukintel.uk. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 10 tools, including uk_preview, uk_health, uk_company_search, uk_company_profile, uk_company_verdict.
Companies House and Find a Grant as paid JSON for agents. USDC via x402, no signup.
361 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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=grants for a real grant eligibility verdict, also 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/grants/{id}/eligibility with ?wing=grants.
| Parameter | Type | Description |
|---|---|---|
| wing | string | Which product family to sample: company (default) or grants. |
{
"name": "uk_preview",
"title": "A real sample answer, rotating daily (free)",
"description": "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=grants for a real grant eligibility verdict, also rotating daily. Every response carries the same envelope: query, result, verdict, confidence, as_of, sources, attribution, notice, cost.\n\nFree. Returns: The identical envelope returned by the paid endpoints: /v1/company/{number}/verdict by default, /v1/grants/{id}/eligibility with ?wing=grants.",
"inputSchema": {
"type": "object",
"properties": {
"wing": {
"enum": [
"company",
"grants"
],
"type": "string",
"description": "Which product family to sample: company (default) or grants."
}
},
"additionalProperties": false
}
}Liveness and upstream health. Free, because frameworks probe before they route money. Free. Returns: status, version, network, upstreams{}, rules_version, warnings[].
No parameters.
{
"name": "uk_health",
"title": "Service status (free)",
"description": "Liveness and upstream health. Free, because frameworks probe before they route money.\n\nFree. Returns: status, version, network, upstreams{}, rules_version, warnings[].",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| q * | string | Company name or fragment to search for. |
| limit | integer | Number of matches to return, 1-5. Defaults to 5. |
{
"name": "uk_company_search",
"title": "Search UK companies by name",
"description": "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.\n\nCosts $0.005 USDC per call (x402, Base mainnet). Returns: results[] of { company_number, name, status, incorporated, address_snippet }, plus total_matches.",
"inputSchema": {
"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
}
}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 }.
| Parameter | Type | Description |
|---|---|---|
| detail | string | Set to 'full' to add filing history (last 10) and anonymised officer records, and to lift the ~800 token response cap. |
| number * | string | UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP). |
{
"name": "uk_company_profile",
"title": "Structured UK company profile",
"description": "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.\n\nCosts $0.02 USDC per call (x402, Base mainnet). Returns: result = { name, company_number, status, type, incorporated, registered_office, sic_codes[], accounts{}, confirmation_statement{}, officers{ active, total, resigned_last_12m }, age_years }.",
"inputSchema": {
"type": "object",
"required": [
"number"
],
"properties": {
"detail": {
"enum": [
"full"
],
"type": "string",
"description": "Set to 'full' to add filing history (last 10) and anonymised officer records, and to lift the ~800 token response cap."
},
"number": {
"type": "string",
"pattern": "^([A-Z]{2})?[0-9]{6,8}$",
"description": "UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP)."
}
},
"additionalProperties": false
}
}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 }.
| Parameter | Type | Description |
|---|---|---|
| detail | string | Set to 'full' to add filing history (last 10) and anonymised officer records, and to lift the ~800 token response cap. |
| number * | string | UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP). |
{
"name": "uk_company_verdict",
"title": "0-100 legitimacy verdict on a UK company",
"description": "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.\n\nCosts $0.10 USDC per call (x402, Base mainnet). Returns: Everything the profile returns, plus verdict = { score 0-100, band low_risk|caution|high_risk, flags[{code,detail}], fca{}, narrative }.",
"inputSchema": {
"type": "object",
"required": [
"number"
],
"properties": {
"detail": {
"enum": [
"full"
],
"type": "string",
"description": "Set to 'full' to add filing history (last 10) and anonymised officer records, and to lift the ~800 token response cap."
},
"number": {
"type": "string",
"pattern": "^([A-Z]{2})?[0-9]{6,8}$",
"description": "UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP)."
}
},
"additionalProperties": false
}
}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.
| Parameter | Type | Description |
|---|---|---|
| number * | string | UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP). |
{
"name": "uk_company_fca",
"title": "FCA Financial Services Register status only",
"description": "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.\n\nCosts $0.02 USDC per call (x402, Base mainnet). Returns: result.fca = { checked, regulated, frn, firm_name, status, permissions_summary, warnings[], note }. When the register is unavailable, checked=false and the reason is named - never a 500.",
"inputSchema": {
"type": "object",
"required": [
"number"
],
"properties": {
"number": {
"type": "string",
"pattern": "^([A-Z]{2})?[0-9]{6,8}$",
"description": "UK company number. 8 characters; two-letter prefixes are supported (SC = Scotland, NI = Northern Ireland, OC = LLP)."
}
},
"additionalProperties": false
}
}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{} }.
| Parameter | Type | Description |
|---|---|---|
| q | string | Keywords matched against grant names, summaries, funders and descriptions (light stemming). At least one criterion is required. |
| max | integer | Only grants whose minimum award is at most this many GBP. |
| min | integer | Only grants whose maximum award is at least this many GBP. |
| region | string | UK nation: england, scotland, wales, northern-ireland (or uk for UK-wide only). |
| open_now | string | Default true: only grants currently open for applications. Set to false to include closed/not-yet-open listings. |
| org_type | string | Applicant type: individual, business, charity, community_group, public_body, local_authority, education (synonyms like sole-trader, cic, council are mapped). |
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} }.
| Parameter | Type | Description |
|---|---|---|
| top | integer | |
| project * | object | The project profile to match against live grants. |
{
"name": "uk_grants_match",
"title": "Match a project profile to eligible UK grants, ranked",
"description": "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.\n\nCosts $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} }.",
"inputSchema": {
"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
}
}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[] }.
| Parameter | Type | Description |
|---|---|---|
| id * | string | 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 | string | Where the project is: england, scotland, wales, northern-ireland. |
| declare | object | 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. |
| org_type | string | Applicant type slug (individual, business, charity, community_group, public_body, local_authority, education). |
{
"name": "uk_grant_eligibility",
"title": "ELIGIBLE / UNCERTAIN / INELIGIBLE verdict for one grant, one project",
"description": "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.\n\nCosts $0.15 USDC per call (x402, Base mainnet). Returns: result = { grant{name,funder,window,amounts,source_url}, criteria[{code,requirement,pass,detail}], missing[], failed[], indicative_funding, criteria_provenance{source,complete,parsed_at,eligibility_text_available} }, verdict = { score, band eligible|uncertain|ineligible, flags[] }.",
"inputSchema": {
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{1,120}$",
"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
}
}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 }.
| Parameter | Type | Description |
|---|---|---|
| name * | string | Funder name or slug, e.g. national-lottery-heritage-fund, "Esmée Fairbairn Foundation", or a GB-CHC-… org id. |
{
"name": "uk_funder_dossier",
"title": "Funder dossier from 1.4M+ published UK grants",
"description": "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).\n\nCosts $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 }.",
"inputSchema": {
"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
}
}Pay-per-call UK intelligence for AI agents, as clean JSON. Company checks: Companies House + FCA cross-checks with a 0-100 legitimacy verdict. 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 the payment in _meta["x402/payment"]. An x402-aware MCP client does this for you. Start with uk_preview - it is free and returns a real, freshly-computed answer in the exact shape the paid tools return, so you can check the response before spending anything. Information, not advice.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
{
"name": "uk_grants_search",
"title": "Search live UK grants",
"description": "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.\n\nCosts $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{} }.",
"inputSchema": {
"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
}
}