Skip to main content
hc
Submit
mcpSource-backed

Algolia MCP Server for Claude

Connect Claude to Algolia-managed MCP servers for curated public search and recommendation access or internal, user-scoped search and analytics workflows.

by Algolia · submitted by MkDev11·added 2026-06-05·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

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/algolia-mcp-server
Source URLs
https://www.algolia.com/doc/guides/model-context-protocol, https://github.com/JSONbored/awesome-claude/blob/main/content/mcp/algolia-mcp-server.mdx, https://www.algolia.com/
Safety notes
Algolia documents two Algolia-managed MCP offerings. Public MCP is for curated search and recommendation access to selected indices; Productivity MCP is for internal, user-scoped workflows that inherit the signed-in user's Algolia permissions., Algolia describes Public MCP as a beta feature under its Beta Services terms. Treat setup behavior, limits, dashboard controls, and client support as changeable until Algolia marks the feature generally available., Public MCP uses a generated server URL for a specific Algolia application and selected indices. Do not publish that URL in public repositories, issues, logs, screenshots, or client configs unless the exposed records are intended for that audience., Public MCP client configuration does not require client-side authentication, so the selected Search API key restrictions, selected indices, Recommend models, and index descriptions are the primary controls., Productivity MCP is documented as read-only for analysis and exploration, but it can expose anything the signed-in user can access in Algolia. Use a least-privilege account for sensitive projects., Algolia says MCP usage counts toward the existing Algolia plan. Monitor API usage and avoid broad automated loops, high-traffic prompts, or repeated large searches through an MCP client.
Privacy notes
Algolia MCP can return search hits, object attributes, facet values, recommendations, index names, analytics metrics, top searches, no-result queries, countries, click positions, user counts, and other search performance data into the model conversation., Public MCP exposes records according to the configured indices and Search API key permissions. Remove private object attributes or use secured, filtered, or separate indices before connecting customer-facing agents., Productivity MCP uses the signed-in user's Algolia identity and permissions. Treat prompts, outputs, screenshots, and MCP client logs as internal data whenever they include Algolia analytics, index names, or object records., Do not paste Admin API keys, write API keys, private secured API keys, customer identifiers, unreleased product catalog fields, pricing rules, personal data, or raw exports into prompts or PR comments., Algolia recommends prompt guidance that preserves result fidelity. Avoid asking the assistant to filter, reorder, or summarize returned hits when an exact search result order matters.
Author
Algolia
Submitted by
MkDev11
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

78

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done

  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

10 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

6 to clear

Platforms

4 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 16/100. Use staged verification before broader rollout.

Risk 16

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    Listing has review metadata.

    Done

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done

  • Review privacy notesRequired

    Privacy notes are present.

    Done

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (5/6 signals complete).

Risk 15

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

5/6 steps complete with no blocking gaps for this preset.

Risk 14

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Prerequisite readiness

Prerequisite readiness

6 prerequisites to line up before setup. Have accounts and credentials ready first.

0/6 ready
Account & credentials2Install & runtime1Permissions & scopes2Network & hosting110 minutes

Safety & privacy surface

Safety & privacy surface

6 safety and 5 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes.

5 areas
  • SafetyPermissions & scopesAlgolia documents two Algolia-managed MCP offerings. Public MCP is for curated search and recommendation access to selected indices; Productivity MCP is for internal, user-scoped workflows that inherit the signed-in user's Algolia permissions.
  • SafetyGeneralAlgolia describes Public MCP as a beta feature under its Beta Services terms. Treat setup behavior, limits, dashboard controls, and client support as changeable until Algolia marks the feature generally available.
  • SafetyData retentionPublic MCP uses a generated server URL for a specific Algolia application and selected indices. Do not publish that URL in public repositories, issues, logs, screenshots, or client configs unless the exposed records are intended for that audience.
  • SafetyCredentials & tokensPublic MCP client configuration does not require client-side authentication, so the selected Search API key restrictions, selected indices, Recommend models, and index descriptions are the primary controls.
  • SafetyGeneralProductivity MCP is documented as read-only for analysis and exploration, but it can expose anything the signed-in user can access in Algolia. Use a least-privilege account for sensitive projects.
  • SafetyGeneralAlgolia says MCP usage counts toward the existing Algolia plan. Monitor API usage and avoid broad automated loops, high-traffic prompts, or repeated large searches through an MCP client.
  • PrivacyTelemetryAlgolia MCP can return search hits, object attributes, facet values, recommendations, index names, analytics metrics, top searches, no-result queries, countries, click positions, user counts, and other search performance data into the model conversation.
  • PrivacyCredentials & tokensPublic MCP exposes records according to the configured indices and Search API key permissions. Remove private object attributes or use secured, filtered, or separate indices before connecting customer-facing agents.
  • PrivacyPermissions & scopesProductivity MCP uses the signed-in user's Algolia identity and permissions. Treat prompts, outputs, screenshots, and MCP client logs as internal data whenever they include Algolia analytics, index names, or object records.
  • PrivacyCredentials & tokensDo not paste Admin API keys, write API keys, private secured API keys, customer identifiers, unreleased product catalog fields, pricing rules, personal data, or raw exports into prompts or PR comments.
  • PrivacyGeneralAlgolia recommends prompt guidance that preserves result fidelity. Avoid asking the assistant to filter, reorder, or summarize returned hits when an exact search result order matters.

Safety notes

  • Algolia documents two Algolia-managed MCP offerings. Public MCP is for curated search and recommendation access to selected indices; Productivity MCP is for internal, user-scoped workflows that inherit the signed-in user's Algolia permissions.
  • Algolia describes Public MCP as a beta feature under its Beta Services terms. Treat setup behavior, limits, dashboard controls, and client support as changeable until Algolia marks the feature generally available.
  • Public MCP uses a generated server URL for a specific Algolia application and selected indices. Do not publish that URL in public repositories, issues, logs, screenshots, or client configs unless the exposed records are intended for that audience.
  • Public MCP client configuration does not require client-side authentication, so the selected Search API key restrictions, selected indices, Recommend models, and index descriptions are the primary controls.
  • Productivity MCP is documented as read-only for analysis and exploration, but it can expose anything the signed-in user can access in Algolia. Use a least-privilege account for sensitive projects.
  • Algolia says MCP usage counts toward the existing Algolia plan. Monitor API usage and avoid broad automated loops, high-traffic prompts, or repeated large searches through an MCP client.

Privacy notes

  • Algolia MCP can return search hits, object attributes, facet values, recommendations, index names, analytics metrics, top searches, no-result queries, countries, click positions, user counts, and other search performance data into the model conversation.
  • Public MCP exposes records according to the configured indices and Search API key permissions. Remove private object attributes or use secured, filtered, or separate indices before connecting customer-facing agents.
  • Productivity MCP uses the signed-in user's Algolia identity and permissions. Treat prompts, outputs, screenshots, and MCP client logs as internal data whenever they include Algolia analytics, index names, or object records.
  • Do not paste Admin API keys, write API keys, private secured API keys, customer identifiers, unreleased product catalog fields, pricing rules, personal data, or raw exports into prompts or PR comments.
  • Algolia recommends prompt guidance that preserves result fidelity. Avoid asking the assistant to filter, reorder, or summarize returned hits when an exact search result order matters.

Prerequisites

  • Algolia account with access to the applications and indices you want Claude to use.
  • MCP-capable client with remote HTTP transport support, such as Claude, Claude Code, ChatGPT, Cursor, VS Code, Gemini CLI, Codex, OpenAI Playground, or another compatible client.
  • For Algolia Productivity MCP, access to enable Productivity MCP in the Algolia dashboard and sign in through the MCP client when prompted.
  • For Algolia Public MCP, an Algolia application with at least one index and the dashboard permission to create or copy a Public MCP server URL.
  • Decision on whether the workflow should use Public MCP for curated application-scoped access or Productivity MCP for internal user-scoped analysis.
  • Review of Algolia plan usage, Search API key permissions, index descriptions, and prompt/result handling before exposing production indices to AI clients.

Schema details

Install type
cli
Troubleshooting
No
Collection metadata
Estimated setup
10 minutes
Difficulty
intermediate
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "algolia": {
      "transport": "http",
      "url": "https://mcp.algolia.com/mcp"
    }
  }
}

About this resource

Content

Algolia MCP Server is Algolia's managed Model Context Protocol support for connecting AI assistants to Algolia search and analytics workflows. Algolia documents two managed offerings:

  • Algolia Public MCP exposes selected indices and Recommend models through an application-scoped MCP URL for AI-facing search and recommendation use cases.
  • Algolia Productivity MCP exposes internal, user-scoped search and analytics tools through https://mcp.algolia.com/mcp after the user signs in.

Use Public MCP when the assistant should search a curated set of records, such as product discovery, documentation search, support answers, or customer-facing AI experiences. Use Productivity MCP when a team member wants Claude to inspect top searches, no-result queries, click positions, countries, users, or index data that the signed-in Algolia account can already access.

Features

  • Algolia-managed MCP services, not a self-hosted integration requirement.
  • Public MCP for selected indices and Recommend models.
  • Productivity MCP for internal, user-scoped search and analytics exploration.
  • Claude custom connector setup for both Public MCP and Productivity MCP.
  • Claude Code setup for Productivity MCP with remote HTTP transport.
  • Codex, Cursor, VS Code, Gemini CLI, ChatGPT, and OpenAI Playground setup paths documented by Algolia.
  • Public MCP URL pattern: https://{APP_ID}.algolia.net/mcp/1/{UNIQ_ID}/mcp.
  • Productivity MCP URL: https://mcp.algolia.com/mcp.
  • Public MCP tools for search, facet values, recommendations, and ChatGPT search/fetch compatibility.
  • Productivity MCP tools for listing/searching indices, recommendations, and analytics such as top searches, no-result queries, click positions, filters, countries, users, and top hits.
  • Existing Algolia plan usage applies to MCP calls.

Installation

Productivity MCP for Claude Code

Enable Algolia Productivity MCP in the Algolia dashboard, then register the remote MCP server:

claude mcp add --transport http algolia https://mcp.algolia.com/mcp

Start a Claude Code session, run /mcp, and sign in when prompted to authorize Algolia.

Productivity MCP Client Config

Use this remote HTTP configuration for MCP clients that accept JSON configuration:

{
  "mcpServers": {
    "algolia": {
      "transport": "http",
      "url": "https://mcp.algolia.com/mcp"
    }
  }
}

The client should prompt for OAuth-style sign-in. Algolia's docs say no OAuth client ID or client secret is needed when the client asks for those fields.

Public MCP Client Config

Create or copy a Public MCP server URL from the Algolia dashboard, then add it to your MCP client:

{
  "mcpServers": {
    "Algolia": {
      "url": "https://{APP_ID}.algolia.net/mcp/1/{UNIQ_ID}/mcp"
    }
  }
}

For Claude, add the copied URL as a custom connector remote MCP server URL and leave advanced settings empty.

Use Cases

  • Let a customer-facing assistant search only the curated product, help center, or documentation indices selected for Public MCP.
  • Ask Claude to return Algolia hits exactly as provided for a search or support workflow.
  • Explore top searches and no-result queries before planning synonyms, rules, content fixes, or index changes.
  • Review click positions, no-click rate, top countries, top filters, and top hits while diagnosing search relevance.
  • Validate which indices and attributes are visible before adding a new AI search experience.
  • Compare recommendation results from selected Recommend models without building a separate integration.
  • Use Productivity MCP for one-off internal analysis while keeping production updates in the Algolia dashboard or APIs.

Safety Checklist

  • Choose Public MCP for a deliberately curated external-facing surface.
  • Choose Productivity MCP only for internal users whose Algolia permissions are appropriate for the data being queried.
  • For Public MCP, select only the indices and Recommend models that the agent should use.
  • Add descriptions that help the LLM choose the right index or tool.
  • Confirm Search API key restrictions before exposing a Public MCP URL.
  • Keep generated Public MCP URLs out of public code, logs, tickets, and screenshots.
  • Monitor Algolia usage because MCP calls count toward the existing plan.
  • Use prompt instructions that preserve Algolia result order and content when exact search results matter.

Source Links

#algolia#search#recommendations#analytics#mcp

Source citations

Add this badge to your README

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

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

How it compares

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

2 trust signals differ across this comparison (Source provenance, Submitter).

Field
Algolia MCP Server for Claude

Connect Claude to Algolia-managed MCP servers for curated public search and recommendation access or internal, user-scoped search and analytics workflows.

Open dossier
Meilisearch MCP Server for Claude

Connect Claude to Meilisearch — manage indexes, add and search documents, tune settings, and monitor tasks — with Meilisearch's official Model Context Protocol server.

Open dossier
Baselight MCP Server for Claude

Official Baselight remote MCP server for searching and querying a catalog of 70,000+ public datasets from Claude via OAuth or x-api-key authentication.

Open dossier
data.gouv.fr logodata.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
Next steps
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceDiffersSource-backedSource-backedSubmission linkedSource submissionSource-backed
SubmitterDiffersMkDev11—kiannidevoktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Brand———data.gouv.fr logodata.gouv.fr
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorAlgoliaMeilisearchBaselightdata.gouv.fr
Added2026-06-052026-06-172026-06-142026-06-06
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✓Algolia documents two Algolia-managed MCP offerings. Public MCP is for curated search and recommendation access to selected indices; Productivity MCP is for internal, user-scoped workflows that inherit the signed-in user's Algolia permissions. Algolia describes Public MCP as a beta feature under its Beta Services terms. Treat setup behavior, limits, dashboard controls, and client support as changeable until Algolia marks the feature generally available. Public MCP uses a generated server URL for a specific Algolia application and selected indices. Do not publish that URL in public repositories, issues, logs, screenshots, or client configs unless the exposed records are intended for that audience. Public MCP client configuration does not require client-side authentication, so the selected Search API key restrictions, selected indices, Recommend models, and index descriptions are the primary controls. Productivity MCP is documented as read-only for analysis and exploration, but it can expose anything the signed-in user can access in Algolia. Use a least-privilege account for sensitive projects. Algolia says MCP usage counts toward the existing Algolia plan. Monitor API usage and avoid broad automated loops, high-traffic prompts, or repeated large searches through an MCP client.✓Tools create and delete indexes and documents and rotate API keys — scope the key and confirm destructive actions. Settings and index deletes change live search behavior; review before running them through Claude.✓Query tools may return large result sets; scope filters to avoid excessive data transfer. Some datasets are community-contributed; validate schema and quality before production use. OAuth tokens and API keys grant persistent catalog access until revoked. Do not run unreviewed SQL-like queries against sensitive production mirrors without safeguards.✓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✓Algolia MCP can return search hits, object attributes, facet values, recommendations, index names, analytics metrics, top searches, no-result queries, countries, click positions, user counts, and other search performance data into the model conversation. Public MCP exposes records according to the configured indices and Search API key permissions. Remove private object attributes or use secured, filtered, or separate indices before connecting customer-facing agents. Productivity MCP uses the signed-in user's Algolia identity and permissions. Treat prompts, outputs, screenshots, and MCP client logs as internal data whenever they include Algolia analytics, index names, or object records. Do not paste Admin API keys, write API keys, private secured API keys, customer identifiers, unreleased product catalog fields, pricing rules, personal data, or raw exports into prompts or PR comments. Algolia recommends prompt guidance that preserves result fidelity. Avoid asking the assistant to filter, reorder, or summarize returned hits when an exact search result order matters.✓Indexed documents and search results enter the MCP client context and the model's prompt. MEILI_HTTP_ADDR and MEILI_MASTER_KEY are secrets — keep them in the client config or environment.✓Search terms and query filters are sent to Baselight and may appear in usage logs. Dataset rows returned through MCP may include PII or licensed third-party content subject to dataset terms. Avoid pasting raw dataset excerpts containing personal data into public channels.✓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.
Prerequisites
  • Algolia account with access to the applications and indices you want Claude to use.
  • MCP-capable client with remote HTTP transport support, such as Claude, Claude Code, ChatGPT, Cursor, VS Code, Gemini CLI, Codex, OpenAI Playground, or another compatible client.
  • For Algolia Productivity MCP, access to enable Productivity MCP in the Algolia dashboard and sign in through the MCP client when prompted.
  • For Algolia Public MCP, an Algolia application with at least one index and the dashboard permission to create or copy a Public MCP server URL.
  • A reachable Meilisearch instance URL (MEILI_HTTP_ADDR).
  • A Meilisearch master or API key (MEILI_MASTER_KEY) when your instance requires authentication.
  • uv (uvx) or pip to run meilisearch-mcp, or Docker (getmeili/meilisearch-mcp).
  • An MCP client such as Claude Code or Claude Desktop.
  • Baselight account with API access or OAuth authorisation for dataset queries.
  • Claude Pro, Team, or Enterprise with Connectors support, or another MCP client with remote HTTP connectors.
  • Understanding of the dataset topics you plan to query to narrow catalog searches effectively.
  • Compliance review if exported dataset rows may contain regulated or personal data.
  • 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.
Install
claude mcp add --transport http algolia https://mcp.algolia.com/mcp
claude mcp add meilisearch -e MEILI_HTTP_ADDR=<your-meili-url> -e MEILI_MASTER_KEY=<your-key> -- uvx -n meilisearch-mcp
claude mcp add --transport http baselight https://api.baselight.app/mcp
claude mcp add --transport http datagouv https://mcp.data.gouv.fr/mcp
Config
{
  "mcpServers": {
    "algolia": {
      "url": "https://mcp.algolia.com/mcp",
      "type": "http"
    }
  }
}
{
  "mcpServers": {
    "meilisearch": {
      "command": "uvx",
      "args": ["-n", "meilisearch-mcp"],
      "env": {
        "MEILI_HTTP_ADDR": "<your-meili-url>",
        "MEILI_MASTER_KEY": "<your-key>"
      }
    }
  }
}
{
  "mcpServers": {
    "baselight": {
      "url": "https://api.baselight.app/mcp",
      "type": "http",
      "headers": {
        "x-api-key": "YOUR_BASELIGHT_API_KEY"
      }
    }
  }
}
{
  "mcpServers": {
    "datagouv": {
      "url": "https://mcp.data.gouv.fr/mcp",
      "type": "http"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Source-backed guides for putting this to work.

Auditing MCP Client Configuration Before Team Rollout

Audit MCP client configuration before sharing it with a team.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by YB0y

Building In-Process MCP Tools with the Claude Agent SDK

Define in-process MCP tools for the Claude Agent SDK with createSdkMcpServer and the tool helper, then wire them into query.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by JPette1783

Choose the Right Claude Extension Surface

Decide when to use Claude subagents, skills, commands, hooks, or MCP.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by MkDev11

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.