Inkeep RAG
Inkeep MCP Server enables Claude to search and retrieve relevant documentation through Inkeep's RAG API. The server exposes a single 'rag-search' tool that queries Inkeep's API using the OpenAI client library, returning structured citation data compatible with Claude's citation format. It requires an Inkeep account and API key, and is configured through environment variables. This implementation is particularly valuable for workflows where users need to reference documentation without leaving their conversation with Claude, making it ideal for technical support, developer assistance, and knowledge-based interactions.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/inkeep/mcp-server-python
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Inkeep RAG from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.