Cuisor MCP

Provides an MCP server interface to the Romanian company register, enabling agents to search for companies, retrieve filed financial statements from 2008, check ANAF fiscal status, access public procurement data, and view legal representatives and court records.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by cuisor.ro

You need:Every verb requires an API key on `Authorization: Bearer` or `X-API-Key`.

MCP endpoint (Streamable HTTP)

https://cuisor.ro/mcp

Vendor documentation

What its tools do

12 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (12)

search_companies
get_company
get_financials
get_procurement
get_officers
get_legal
resolve_caen
list_companies
company_stats
get_meta
search
fetch

12 of 12 have a description · 0 of 12 declare behavior hints · 0 of 11 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 4:01 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Search for companies by name or CUI
Retrieve filed financial statements and fiscal status
Access public procurement and court records
Resolve CAEN activity codes and get company statistics

Source and maintenance

Community listingRegistry 1.29.1

mcp-registry: io.github.idragulin/cuisor@1.29.1 Project website

Protocol and capabilities

Server: cuisor 1.29.1
MCP protocol negotiated in check: 2025-11-25
Tools: 12 advertised
Resources: 0 advertised
Resource templates: 0 advertised
Prompts: 0 advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Look up Romanian companies by name or CUI (fiscal code), read their filed financials, fiscal standing, procurement history and legal representatives, and compute aggregates across filtered populations. Data: the Romanian company register (~4M companies) with filed financial statements, ANAF fiscal status, public procurement awards, and legal representatives. Amounts are in lei (RON). Not real-time: every payload states the age of the data it came from.

Tools

12 advertised

search_companies

Advertised by the server during the last successful anonymous check.

Resolve a company name or CUI to candidate companies. Use this first whenever the user names a company rather than giving its CUI. Returns at most 50 candidates, active companies first, largest turnover first. Romanian company names collide heavily, so show the user the candidates rather than assuming the first is right. An unquoted query matches every name containing the words (mina srl: 1015 companies); wrap a name you already know in double quotes to get only the companies called that ("mina srl": 14). Case, diacritics and SRL/S.R.L. all fold. Quote a name, not a CUI.

search_companies input schema

{
  "type": "object",
  "title": "search_companies_toolArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10
    },
    "query": {
      "type": "string",
      "title": "Query"
    }
  }
}

get_company

Advertised by the server during the last successful anonymous check.

Identity, status, address, activity and headline figures for one company by CUI. Slim by default. Pass include=['financials','procurement','change_history','peers','same_address'] for more. Carries `as_of` dates: the register and ANAF are refreshed on different schedules. Data: the Romanian company register (~4M companies) with filed financial statements, ANAF fiscal status, public procurement awards, and legal representatives. Amounts are in lei (RON). Not real-time: every payload states the age of the data it came from.

get_company input schema

{
  "type": "object",
  "title": "get_company_toolArguments",
  "required": [
    "cui"
  ],
  "properties": {
    "cui": {
      "type": "string",
      "title": "Cui"
    },
    "include": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Include",
      "default": null
    }
  }
}

get_financials

Advertised by the server during the last successful anonymous check.

Every filed financial year for one company: turnover, profit (signed — negative is a loss), employees, and the full balance sheet, all in lei. `latest_filed_year` says how recent the filings go, so a year with no row reads as 'not filed yet' rather than 'no data'.

get_financials input schema

{
  "type": "object",
  "title": "get_financials_toolArguments",
  "required": [
    "cui"
  ],
  "properties": {
    "cui": {
      "type": "string",
      "title": "Cui"
    }
  }
}

get_procurement

Advertised by the server during the last successful anonymous check.

Public procurement (SEAP) awards for one company: contracts it won, and contracts it granted as a contracting authority. Bounded to the 200 most recent per side; `total` reports the true count, which can be far larger.

get_procurement input schema

{
  "type": "object",
  "title": "get_procurement_toolArguments",
  "required": [
    "cui"
  ],
  "properties": {
    "cui": {
      "type": "string",
      "title": "Cui"
    },
    "role": {
      "type": "string",
      "title": "Role",
      "default": "both"
    }
  }
}

get_officers

Advertised by the server during the last successful anonymous check.

Legal representatives and administrators of one company. This is personal data: it requires an API key, every call is recorded against that key, and it is never available anonymously. `sources_present` says which registers contributed, so an empty list means 'none on record from these sources', not 'this company has no officers'.

get_officers input schema

{
  "type": "object",
  "title": "get_officers_toolArguments",
  "required": [
    "cui"
  ],
  "properties": {
    "cui": {
      "type": "string",
      "title": "Cui"
    }
  }
}

get_legal

Advertised by the server during the last successful anonymous check.

Court dockets (portal.just.ro) and BPI publications for one company, by CUI. Covers roughly the last three years, not a complete litigation history — it answers whether a company is in court now or recently, not whether it has ever been sued. Includes ambiguous matches the public website never shows: a docket whose party name is shared by more than one company in the register, fanned out one row per candidate CUI. No co-party names, no outcome or merits.

get_legal input schema

{
  "type": "object",
  "title": "get_legal_toolArguments",
  "required": [
    "cui"
  ],
  "properties": {
    "cui": {
      "type": "string",
      "title": "Cui"
    }
  }
}

resolve_caen

Advertised by the server during the last successful anonymous check.

Resolve free text like 'coffee shops' or 'car repair' to CAEN activity codes. ALWAYS call this before filtering by activity — do not guess a CAEN code. More than half the official nomenclator is obsolete CAEN Rev.1 with zero companies, and those are exactly the entries whose descriptions match the obvious word, so a guessed code commonly returns nothing for a question with thousands of answers. Show the user what was matched.

resolve_caen input schema

{
  "type": "object",
  "title": "resolve_caen_toolArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10
    },
    "query": {
      "type": "string",
      "title": "Query"
    }
  }
}

list_companies

Advertised by the server during the last successful anonymous check.

List companies matching a filter, largest turnover first, at most 100 per page. Pass caen_query for free text ('coffee shops') or caen for explicit codes; judet accepts 'Bucharest', 'Bucuresti' or 'Bucureşti'; cui takes up to 100 comma-separated CUIs. Filters compose, so 'restaurants registered in Cluj last week' is one call. For newly registered companies pass sort='registered_desc' with registered_after — the default turnover order puts them behind every company that has ever filed a figure. Check register.data_through in the response before reporting an empty result: the register is a monthly ONRC snapshot and holds nothing registered after that date. Use cursor to page. If you want a count, an average or a total, use company_stats instead — do not page through companies to compute one.

list_companies input schema

{
  "type": "object",
  "title": "list_companies_toolArguments",
  "properties": {
    "cui": {
      "type": "string",
      "title": "Cui",
      "default": ""
    },
    "caen": {
      "type": "string",
      "title": "Caen",
      "default": ""
    },
    "sort": {
      "type": "string",
      "title": "Sort",
      "default": "turnover_desc"
    },
    "judet": {
      "type": "string",
      "title": "Judet",
      "default": ""
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 25
    },
    "cursor": {
      "type": "string",
      "title": "Cursor",
      "default": ""
    },
    "status": {
      "type": "string",
      "title": "Status",
      "default": ""
    },
    "caen_query": {
      "type": "string",
      "title": "Caen Query",
      "default": ""
    },
    "min_turnover": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Min Turnover",
      "default": null
    },
    "min_employees": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Min Employees",
      "default": null
    },
    "registered_after": {
      "type": "string",
      "title": "Registered After",
      "default": ""
    },
    "registered_before": {
      "type": "string",
      "title": "Registered Before",
      "default": ""
    }
  }
}

company_stats

Advertised by the server during the last successful anonymous check.

Compute ONE number over a filtered population of companies — count, sum, avg, median, p25, p75, min or max. Prefer this over listing companies and doing the arithmetic yourself: it is one call instead of dozens, and it is exact. metric: net_turnover_ron, net_profit_ron, employees, sales_per_employee_ron, profit_margin_pct, company_count, age_years. group_by: year, caen, judet, status, founded_year — use group_by='year' with years='2019-2024' to get a time series you can chart. Always report `coverage.rows_with_metric` alongside the answer: it is routinely about half of `coverage.matched_companies`, because many companies never filed the figure.

company_stats input schema

{
  "type": "object",
  "title": "company_stats_toolArguments",
  "properties": {
    "agg": {
      "type": "string",
      "title": "Agg",
      "default": "avg"
    },
    "cui": {
      "type": "string",
      "title": "Cui",
      "default": ""
    },
    "caen": {
      "type": "string",
      "title": "Caen",
      "default": ""
    },
    "year": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "Year",
      "default": null
    },
    "judet": {
      "type": "string",
      "title": "Judet",
      "default": ""
    },
    "years": {
      "type": "string",
      "title": "Years",
      "default": ""
    },
    "metric": {
      "type": "string",
      "title": "Metric",
      "default": "net_turnover_ron"
    },
    "status": {
      "type": "string",
      "title": "Status",
      "default": ""
    },
    "group_by": {
      "type": "string",
      "title": "Group By",
      "default": ""
    },
    "caen_query": {
      "type": "string",
      "title": "Caen Query",
      "default": ""
    },
    "min_turnover": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Min Turnover",
      "default": null
    },
    "registered_after": {
      "type": "string",
      "title": "Registered After",
      "default": ""
    }
  }
}

get_meta

Advertised by the server during the last successful anonymous check.

How old each dataset is, how many companies filed in each year, what fraction of the register carries an activity code, and the mapping from every financial field name to its Romanian label. Call this when the user asks how current or how complete the data is.

get_meta input schema

{
  "type": "object",
  "title": "get_meta_toolArguments",
  "properties": {}
}

search

Advertised by the server during the last successful anonymous check.

ChatGPT connector search: find Romanian companies by name or CUI, returned as {id, title, url}. Identical to search_companies — use that tool instead unless you are the ChatGPT Apps SDK connector, which requires this exact name.

search input schema

{
  "type": "object",
  "title": "search_toolArguments",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "title": "Query"
    }
  }
}

fetch

Advertised by the server during the last successful anonymous check.

ChatGPT connector fetch: the full company document for one CUI `id`, as returned by a prior `search` call. Identical to get_company with no include= (administrators included; get_officers lists them per source). Use get_company instead unless you are the ChatGPT Apps SDK connector, which requires this exact name.

fetch input schema

{
  "type": "object",
  "title": "fetch_toolArguments",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "title": "Id"
    }
  }
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (5 of 5 answered).

2026-11-06: 1 of 1 checks answered
2026-11-07: 2 of 2 checks answered
2026-11-09: 1 of 1 checks answered
2026-11-10: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 1837 ms
95th percentile latency: 1837 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 4:01 PM UTC · probe · passed · 1837 ms · metadata changed · 12 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http cuisor-mcp https://cuisor.ro/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add cuisor-mcp --url https://cuisor.ro/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable cuisor-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "cuisor-mcp": {
      "url": "https://cuisor.ro/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "cuisor-mcp": {
      "type": "streamableHttp",
      "url": "https://cuisor.ro/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start cuisor-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "cuisor-mcp": {
      "type": "http",
      "url": "https://cuisor.ro/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http cuisor-mcp https://cuisor.ro/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://cuisor.ro/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "cuisor-mcp": {
      "serverUrl": "https://cuisor.ro/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Cuisor MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows