An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Paris Grants Voted Association Subvention to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Query over 100,000 public subvention records instantly.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Paris Open Data.

  1. 01

    Grants by direction

    This capability counts grants for a specific granting direction like culture or sports. You can also restrict the count to a single budget year.

  2. 02

    Grants overview

    This capability provides a high-level summary of the entire voted-grants dataset. It returns top beneficiaries, funding types, and granting bodies.

  3. 03

    Grant lookup

    This capability finds a specific grant using its unique file number. It returns the beneficiary, amount, and activity sectors for that exact record.

  4. 04

    Grants by year

    This capability calculates grant totals for specific budget years. It provides the total count for the range and the difference between the first and last year.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Paris Open Data.

  1. 05

    Beneficiary history

    This capability pulls the full funding history for a specific association. You can narrow the results down to a single year if needed.

  2. 06

    Big grants

    This capability identifies the largest grants by filtering for a minimum euro amount. It's the fastest way to find major city funders.

  3. 07

    Count grants

    This capability performs fast counts of grants based on year, direction, type, or amount. Use it to compare funding volumes across different categories.

  4. 08

    List grants

    This capability retrieves detailed rows of grant data including SIRET, budget year, and activity sectors. It supports pagination with limit and offset.

Real work

What teams actually run

01

Investigative Reporting

An investigator asks the agent to find all grants over 500,000 euros for a specific year to spot unusual spending.

02

Association Monitoring

A researcher checks the beneficiary_history of an organization to see if their funding is increasing or decreasing.

03

Budget Comparison

A policy analyst compares the total grants issued by the culture direction versus the sports direction.

04

Data Verification

A user provides a specific file number to get the exact euro amount and type of a single grant.

One connector, every AI

Paris Open Data works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Paris Open Data to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

978ms average. Fast in production.

Paris Open Data is checked daily against the live service.

Daily averagePeak 1339ms
Sep 28Today
Fastest day
677ms
Slowest day
1339ms
14-day trend
Improving-32%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Paris Open Data, so you can see the experience inside your AI.

It does not authenticate your account with Paris Open Data. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Paris Open Data Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_BV1tCsNLrGPwPJrzCjfIf5WMYONIqjEajaZeND2a/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Paris Open Data capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "paris-grants-voted-association-subventions-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_BV1tCsNLrGPwPJrzCjfIf5WMYONIqjEajaZeND2a/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Paris Open Data in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Paris Open Data owners hand off.

This MCP is designed for professionals who need to monitor or analyze municipal spending in Paris.

  • 01

    Civic Journalists

    Use the agent to quickly fact-check association funding and identify major spenders.

  • 02

    Researchers

    Use the agent to pull large datasets on the associative fabric of Paris for academic study.

  • 03

    Policy Analysts

    Use the agent to track how different city departments allocate their budgets over time.

FAQ

Questions Paris Open Data owners ask.

  • 01

    What years of data are included in this MCP?

    The dataset includes voted subventions from 2013 through 2026.

  • 02

    Can I find a specific grant if I have the file number?

    Yes, use the grant_lookup capability with the numero_de_dossier to get specific details on a single grant.

  • 03

    How do I find the largest grants in Paris?

    You can use the big_grants capability and specify a minimum amount to filter for the highest values.

  • 04

    Does this MCP provide association SIRET numbers?

    Yes, the grant records include the SIRET numbers for the beneficiary associations.

  • 05

    Is this data updated in real time?

    The data is pulled from the Paris open data platform, reflecting the records available there.

  • 06

    Do I need an API key?

    No. opendata.paris.fr serves all city datasets anonymously over its Opendatasoft REST API. This MCP defines no credentials and needs nothing configured.

  • 07

    What do the direction codes mean?

    Each grant is issued by a city department identified by a code: DDCT (culture, the largest with ~25,000 files), DAC, DJS (sport, ~12,000), DASES, DAE, DASCO, DFPE, DPSP... grants_overview lists the top directions by count so you can discover the codes.

  • 08

    What grant types exist?

    Five stored values: Fonctionnement (operations), Projet, Investissement, Non précisée and Indéterminée. The nature filter is an exact match on the stored text, accents included.

  • 09

    Does a 0 amount mean nothing was paid?

    montant_vote is the voted amount and the source data contains rows where it is 0. Use a min_amount filter (big_grants, or the same filter on list_grants) to keep only positive grants.

Explore

More in Government Public Data

Suggestions

Connect Paris Open Data to Claude, Cursor, ChatGPT & more