data.gouv.fr MCP Server

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL

https://heyclau.de/entry/mcp/datagouv-mcp-server

Source URLs

https://raw.githubusercontent.com/datagouv/datagouv-mcp/main/README.md, https://github.com/datagouv/datagouv-mcp

Brand

data.gouv.fr

Brand domain

data.gouv.fr

Brand asset source

brandfetch

Safety notes

The hosted endpoint is documented as publicly available without access restrictions, so treat requests and returned public-data context as externally visible., Tools are read-only but can retrieve dataset metadata, resource URLs, rows from tabular resources, service OpenAPI specs, metrics, and organization details that may influence decisions., Public open data can be stale, incomplete, licensed with reuse conditions, or unsuitable for operational decisions without checking the dataset publisher and update cadence., Tabular queries can return rows from large resources; use small page sizes and pagination instead of asking an agent to pull entire datasets through chat., If self-hosting, review MCP_HOST, allowed hosts, allowed origins, Sentry, Matomo, and API-environment settings before exposing the server.

Privacy notes

Search terms, dataset interests, resource IDs, user-agent headers, request URLs, tool names, and returned dataset rows may be visible to the hosted MCP service, MCP client, model provider, and logs., The server includes optional Matomo and Sentry instrumentation in source; hosted deployments may apply their own analytics and error-reporting policies., Public datasets can still contain personal data, geographic sensitivity, business identifiers, or regulated information; review source metadata and reuse terms before sharing results., Avoid placing private investigation notes, customer context, or unpublished analysis inside prompts when a generic dataset search is enough.

Author

data.gouv.fr

Submitted by

oktofeesh1

Claim status

unclaimed

Last verified

2026-06-06

• Search terms, dataset interests, resource IDs, user-agent headers, request URLs, tool names, and returned dataset rows may be visible to the hosted MCP service, MCP client, model provider, and logs.
• The server includes optional Matomo and Sentry instrumentation in source; hosted deployments may apply their own analytics and error-reporting policies.
• Public datasets can still contain personal data, geographic sensitivity, business identifiers, or regulated information; review source metadata and reuse terms before sharing results.
• Avoid placing private investigation notes, customer context, or unpublished analysis inside prompts when a generic dataset search is enough.

• MCP client that supports Streamable HTTP or a remote MCP bridge such as mcp-remote.
• Agreement on whether hosted data.gouv.fr MCP requests may be sent to the public hosted endpoint.
• Public-data review process for datasets that may contain personal, sensitive, stale, or jurisdiction-specific information.
• Python 3.13 or newer only if self-hosting the repository instead of using the hosted endpoint.

Show that data.gouv.fr MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

[![Listed on HeyClaude](https://heyclau.de/badge/mcp/datagouv-mcp-server.svg)](https://heyclau.de/entry/mcp/datagouv-mcp-server)

data.gouv.fr MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field	data.gouv.fr MCP Server Official data.gouv.fr MCP server for searching French national open datasets, exploring organizations and data services, inspecting resources, querying tabular data, and retrieving dataset metrics through Claude. Open dossier	MCP-Brasil Open source MCP server for querying Brazilian public data sources, including economic, legislative, transparency, judicial, electoral, environmental, health, education, public-safety, aviation, and infrastructure datasets. Open dossier	Data API Builder MCP Tools MCP support in Azure Data API Builder for exposing configured database entities as MCP tools, including entity discovery and DML operations over Azure databases and supported on-premises data stores. Open dossier	Google Search Console MCP Server MCP server for Google Search Console that lets Claude list properties, inspect indexing status, query search analytics, compare performance periods, audit sitemaps, and manage Search Console resources with guarded destructive tools. Open dossier
Next steps	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust	Review first	Review first	Review first	Review first
Review status	Not reviewed	Not reviewed	Not reviewed	Not reviewed
Package trust	Package not verified	Package not verified	Package not verified	Package not verified
Source provenance	Source-backed	Source-backed	Source-backed	Source-backed
Submitter	oktofeesh1	oktofeesh1	oktofeesh1	oktofeesh1
Install risk	Review first	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Brand	data.gouv.fr	—	Data API Builder	—
Category	mcp	mcp	mcp	mcp
Source	Source-backed	Source-backed	Source-backed	Source-backed
Author	data.gouv.fr	mcp-brasil contributors	Azure	Amin Foroutan
Added	2026-06-06	2026-06-06	2026-06-06	2026-06-06
Platforms	Claude CodeCodexCursorClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop
Harness	Claude CodeCodexCursorClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop
Source repo	—	—	—	—
Safety notes	✓The hosted endpoint is documented as publicly available without access restrictions, so treat requests and returned public-data context as externally visible. Tools are read-only but can retrieve dataset metadata, resource URLs, rows from tabular resources, service OpenAPI specs, metrics, and organization details that may influence decisions. Public open data can be stale, incomplete, licensed with reuse conditions, or unsuitable for operational decisions without checking the dataset publisher and update cadence. Tabular queries can return rows from large resources; use small page sizes and pagination instead of asking an agent to pull entire datasets through chat. If self-hosting, review MCP_HOST, allowed hosts, allowed origins, Sentry, Matomo, and API-environment settings before exposing the server.	✓MCP-Brasil can query many Brazilian public data sources, some of which cover courts, elections, health, public safety, government contracts, public spending, and regulated sectors. The upstream acceptable-use policy prohibits doxing, stalking, unlawful electoral profiling, sensitive health-data misuse, unauthorized judicial data redistribution, re-identification, fake official claims, and other abusive uses. Outputs should not be treated as official government records without checking the original source, because the MCP server is an independent open source project and LLM clients can misread or hallucinate. Respect each upstream API's rate limits, license, attribution requirements, registration rules, and redistribution restrictions before batching or publishing results. Large local datasets are opt-in and can download sizable public data caches; review disk usage, refresh behavior, and cache retention before enabling them. Keep any optional DataJud, transparency, Meta, Anthropic, OAuth, or static bearer tokens scoped and separated from shared logs or test clients.	✓Data API Builder MCP tools can expose database entity metadata and perform DML operations depending on DAB configuration and permissions. Built-in tools include entity discovery and record read, create, update, delete, aggregate, and execute-style workflows in the MCP source tree. The upstream README still labels endpoint support as coming soon while source, samples, and testing docs expose MCP behavior; verify the exact release before production use. Use least-privilege roles, disable DML tools where not required, and require approval before write, delete, execute, or stored-procedure operations. Do not connect MCP clients to production databases without backups, audit logging, query limits, and rollback procedures.	✓The server requests the Google Search Console webmasters scope and can access every property available to the authenticated account. add_site, delete_site, and delete_sitemap are disabled by default and only run when GSC_ALLOW_DESTRUCTIVE is true. manage_sitemaps can submit or delete sitemaps depending on action and destructive settings. URL inspection and analytics tools can reveal indexing issues, search terms, landing pages, countries, devices, click-through rates, and ranking positions. Use least-privilege service accounts, avoid full-access credentials where read-only analysis is enough, and confirm exact site_url values with list_properties.
Privacy notes	✓Search terms, dataset interests, resource IDs, user-agent headers, request URLs, tool names, and returned dataset rows may be visible to the hosted MCP service, MCP client, model provider, and logs. The server includes optional Matomo and Sentry instrumentation in source; hosted deployments may apply their own analytics and error-reporting policies. Public datasets can still contain personal data, geographic sensitivity, business identifiers, or regulated information; review source metadata and reuse terms before sharing results. Avoid placing private investigation notes, customer context, or unpublished analysis inside prompts when a generic dataset search is enough.	✓Public records can still contain personal data or sensitive context, including judicial parties, health professionals, election candidates, public servants, suppliers, property records, campaign information, or location-linked records. The upstream sources document highlights elevated risk for health, electoral, judicial, education, public-safety, and other datasets; operators remain responsible for LGPD compliance and source-specific terms. Local DuckDB caches, terminal output, MCP client logs, chat transcripts, and exported analysis may retain query terms, public-record results, API keys, and derived datasets. Do not disable PII masking or set `MCP_BRASIL_LGPD_ALLOW_PII` without a documented legal basis and a retention/deletion plan. Attribute public data sources and preserve source context when sharing results with users or publishing downstream analysis.	✓Entity metadata can expose database names, table names, view names, stored procedure names, field names, key fields, relationships, permissions, and role design. Read and DML tool calls can expose or change customer records, internal data, regulated fields, identifiers, audit fields, and business workflow state. Connection strings, role headers, MCP URLs, logs, request bodies, result payloads, and MCP transcripts can contain sensitive operational or personal data. Redact database values, connection details, entity names, role names, and query results before sharing prompts, screenshots, logs, or generated notes.	✓OAuth client secrets, service account JSON, cached token files, Search Console properties, page URLs, query terms, sitemap URLs, countries, devices, clicks, impressions, CTR, and positions can be sensitive. The server stores OAuth tokens under a user config directory unless GSC_CONFIG_DIR is changed. Service account files and OAuth tokens must stay out of prompts, issue comments, logs, screenshots, and repository files. Redact property URLs, query data, page URLs, tokens, credential file paths, and inspection results before sharing MCP transcripts.
Prerequisites	MCP client that supports Streamable HTTP or a remote MCP bridge such as mcp-remote. Agreement on whether hosted data.gouv.fr MCP requests may be sent to the public hosted endpoint. Public-data review process for datasets that may contain personal, sensitive, stale, or jurisdiction-specific information. Python 3.13 or newer only if self-hosting the repository instead of using the hosted endpoint.	Python 3.10 or newer with `uvx` available. Review of the upstream acceptable-use policy and source license notes before using outputs in commercial, journalistic, legal, medical, financial, electoral, or civic-decision workflows. Optional API keys for data sources such as Portal da Transparencia, DataJud, or Meta Ad Library when those features are needed. Optional local dataset cache configuration when enabling large DuckDB-backed datasets through `MCP_BRASIL_DATASETS`.	Reviewed Azure Data API Builder configuration with the MCP runtime section enabled. Supported Azure or on-premises database connection configured through DAB. DAB entity permissions, role headers, DML tool flags, and per-entity MCP settings reviewed before exposing tools. MCP client support for the transport used by the deployed DAB server.	Google Cloud project with the Search Console API enabled. OAuth desktop client secrets JSON or service account JSON stored outside the repository. Google Search Console properties where the authenticated user or service account has access. MCP client that can run uvx or a local Python clone.
Install	claude mcp add --transport http datagouv https://mcp.data.gouv.fr/mcp Copy install	uvx --from mcp-brasil python -m mcp_brasil.server Copy install	Enable the DAB runtime MCP section, start Data API Builder with the reviewed configuration, and connect an MCP client to the configured MCP path. Copy install	Run `uvx mcp-search-console` with either `GSC_OAUTH_CLIENT_SECRETS_FILE` for OAuth or `GSC_CREDENTIALS_PATH` plus `GSC_SKIP_OAUTH=true` for a service account. Copy install
Config	{ "mcpServers": { "datagouv": { "url": "https://mcp.data.gouv.fr/mcp", "type": "http" } } } Copy config	Manual-only setup: claude mcp add mcp-brasil -- uvx --from mcp-brasil python -m mcp_brasil.server Copy config	Manual-only setup: "mcp": { "enabled": true, "path": "/mcp" } Copy config	Manual-only setup: GSC_OAUTH_CLIENT_SECRETS_FILE=<absolute-path-to-client-secrets-json> GSC_CREDENTIALS_PATH=<absolute-path-to-service-account-json> GSC_SKIP_OAUTH=true GSC_ALLOW_DESTRUCTIVE=false Copy config
Citations	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationraw.githubusercontent.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationraw.githubusercontent.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationraw.githubusercontent.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationraw.githubusercontent.com Submitted by oktofeesh12026-06-06 Source methodology →
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed

Source-backed guides for putting this to work.