Search

OpenSearch documents an open-source Model Context Protocol server at docs.opensearch.org/latest/ai-agent-integrations/mcp-server for AI assistants to interact with OpenSearch clusters via MCP tools instead of raw REST. The opensearch-project/opensearch-mcp-server-py package supports stdio (Claude Desktop, Cursor, Kiro) and streaming transports (SSE/Streamable HTTP) with tools for listing indexes, retrieving mappings, running search queries, checking cluster health, and counting documents per docs. Configure single-cluster mode via environment variables or multi-cluster YAML; authentication supports basic auth, IAM, header auth, and mTLS for self-managed OpenSearch, Amazon OpenSearch Service, and Serverless. OpenSearch 3.0+ also ships an experimental in-cluster MCP endpoint at `/_plugins/_ml/mcp` (Streamable HTTP) per ML Commons docs—distinct from the standalone py server for external clients.

The fogx/typesense-mcp project provides a community Model Context Protocol server for querying and managing Typesense search indices via stdio. Configure a TOML file with one or more `[[sources]]` blocks (id, host, api_key, collections patterns, optional readonly, port, protocol) and launch with `npx -y typesense-mcp path/to/typesense-mcp.toml` per the README. Tools include `search` for full-text, vector, or hybrid search; `lookup` for collections, schema, documents, counts, aliases, and synonyms; and `manage` for upserts, deletes, collection/synonym/alias writes when at least one source is not readonly. Collection patterns gate access; readonly sources block writes and hide `manage` when all sources are readonly. A `collection://{source}/{collection}` resource exposes field schemas. Pairs naturally with the Typesense tool entry on this site for agent-driven index exploration.

Algolia documents an official managed Model Context Protocol server at algolia.com/doc/guides/model-context-protocol/productivity-mcp. Connect MCP clients to the remote HTTP endpoint `https://mcp.algolia.com/mcp` with OAuth (enable under Generate AI in the Algolia dashboard; sign in when prompted so the MCP inherits your account permissions). Productivity MCP is user-scoped and read-only per docs—tools cover search (`algolia_search_list_indices`, `algolia_search_index`, `algolia_search_for_facet_values`), Recommend (`algolia_recommendations`), and analytics helpers such as top searches, no-click rates, filter usage, and user counts. Algolia docs distinguish this from Algolia Public MCP for application-scoped, curated index exposure to external agents. Supported clients include ChatGPT, Claude, Claude Code, Cursor, Gemini CLI, VS Code, and OpenAI Playground.

Meilisearch maintains an official Model Context Protocol server in meilisearch/meilisearch-mcp, documented at meilisearch.com/blog/introducing-mcp-server. The Python stdio server connects MCP clients to any running Meilisearch instance via `MEILI_HTTP_ADDR` and optional `MEILI_MASTER_KEY`, with `update-connection-settings` to switch hosts mid-session. Tools cover index management, document ingestion, search (filters, sorting, facets, semantic/hybrid), settings, API keys, tasks, and health checks per the README. Install paths include `uvx meilisearch-mcp`, pip, source, and Docker (`getmeili/meilisearch-mcp`). Meilisearch notes the server is development-oriented and that native Meilisearch MCP transport support is coming.

Elastic documents the recommended Agent Builder Model Context Protocol endpoint at `{KIBANA_URL}/api/agent_builder/mcp` (or `{KIBANA_URL}/s/{SPACE_NAME}/api/agent_builder/mcp` for custom Kibana spaces) per elastic.co/docs/explore-analyze/ai-features/agent-builder/mcp-server. The MCP server exposes built-in and custom Agent Builder tools to Claude Desktop, Cursor, VS Code, and other MCP clients via `npx mcp-remote` with an `Authorization: ApiKey` header. API keys must include the Kibana application privilege `feature_agentBuilder.read` or clients receive HTTP 403. Elastic notes the legacy `elastic/mcp-server-elasticsearch` project is deprecated in favor of this endpoint on Elastic 9.2+ and Elasticsearch Serverless; docs recommend least-privilege index scopes and API key expiration.

Pulls version-tagged library documentation and API references from Context7's database of curated SDK docs. Agents cite current library methods instead of hallucinating from stale training data. Particularly valuable for fast-moving frameworks where docs change frequently.

Connects AI agents to Exa's hosted search engine with capabilities for web search, code search, company research, and intelligent web crawling. Agents get fresher information than training cutoffs without manually browsing. Exa understands content semantics beyond keyword matching.

Adds Firecrawl's web scraping, crawling, mapping, and content extraction capabilities to MCP clients. Agents can fetch clean page content, map entire websites, and build retrieval datasets without HTML parsing boilerplate. Designed for RAG pipelines and competitive research.

Connects AI agents to Hugging Face Hub for discovering models, datasets, papers, and Spaces without leaving the coding environment. Agents can find optimal models for tasks, inspect dataset schemas, and access inference APIs. Accelerates ML development workflows.

Provides real-time web search, intelligent content extraction, site mapping, and web crawling capabilities through Tavily's hosted MCP endpoint. Agents can ground responses with fresh, cited web evidence rather than relying on training cutoffs. Typical workflow involves sending a query and receiving structured snippets with source URLs.

Routes search queries through Brave's privacy-respecting search API for web retrieval and local search capabilities. Agents can ground responses with current information without tracking or profiling. Useful for research, compliance-sensitive queries, and users who prefer not to use Google.