{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_2m6peffqfs5m","handle":"ahnlich-mcp","url":"https://wellknown.network/agents/ahnlich-mcp","links":{"self":"https://wellknown.network/agents/ahnlich-mcp/record.json","html":"https://wellknown.network/agents/ahnlich-mcp","markdown":"https://wellknown.network/agents/ahnlich-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ahnlich-mcp","status":"https://wellknown.network/api/v1/agents/ahnlich-mcp/status","claim":"https://wellknown.network/agents/ahnlich-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ahnlich-mcp/claim.json","badge":"https://wellknown.network/agents/ahnlich-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:ahnlich-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ahnlich-mcp","summary":"MCP server for the Ahnlich vector database","description":"# Ahnlich MCP\n\nAn MCP server that exposes [Ahnlich](https://ahnlich.dev/) vector storage and semantic search to MCP-compatible agents.\n\nAhnlich MCP supports two profiles:\n\n- `db` connects directly to Ahnlich DB and accepts precomputed embeddings.\n- `ai` sends raw text through Ahnlich AI, which generates embeddings and stores them in Ahnlich DB.\n\n## Before you start\n\nAhnlich MCP connects to running Ahnlich services.\n\n| Profile | Required services |\n|---|---|\n| `ai` | Ahnlich DB on port `1369` and Ahnlich AI on port `1370` |\n| `db` | Ahnlich DB on port `1369` |\n\nFollow the [Ahnlich installation guide](https://ahnlich.dev/docs/getting-started/installation/) to start the required services.\n\nThe examples below use the `ai` profile. To supply your own embeddings, replace `--profile ai` with `--profile db`.\n\n## Install from PyPI\n\nThis is the recommended installation method. Install [uv](https://docs.astral.sh/uv/getting-started/installation/), then use `uvx` to run Ahnlich MCP directly from PyPI.\n\nVerify that the required Ahnlich services are available:\n\n```bash\nuvx ahnlich-mcp doctor --profile ai\n```\n\n### Claude Desktop\n\nOpen **Settings → Developer → Edit Config** and add:\n\n```json\n{\n  \"mcpServers\": {\n    \"ahnlich\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"ahnlich-mcp\",\n        \"--profile\",\n        \"ai\"\n      ]\n    }\n  }\n}\n```\n\nRestart Claude Desktop after saving the configuration.\n\nIf Claude Desktop cannot find `uvx`, run `command -v uvx` and use the returned absolute path as `command`.\n\n### Codex\n\nAdd the server from your terminal:\n\n```bash\ncodex mcp add ahnlich -- uvx ahnlich-mcp --profile ai\n```\n\nConfirm that it was added:\n\n```bash\ncodex mcp list\n```\n\nYou can also use `/mcp` inside Codex to inspect the connection.\n\n## Run with Docker\n\nUse Docker when you want the MCP server and its Python dependencies isolated in a container.\n\nThe Ahnlich services must already be running and accessible through their default host ports.\n\nPull the image:\n\n```bash\ndocker pull …","publisher":null,"homepage":null,"repository":null,"version":"0.1.2","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:ahnlich-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.825,"provenance":"derived"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.779,"provenance":"derived"}],"categories":["data","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"ahnlich-mcp","registry":"pypi","observedAt":"2026-09-09T08:22:38.358Z","publishedAt":"2026-08-31T10:44:44.027935Z","latestVersion":"0.1.2"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ahnlich-mcp","url":"https://pypi.org/project/ahnlich-mcp/","firstSeenAt":"2026-09-09T08:21:31.265Z","fetchedAt":"2026-09-09T08:21:31.265Z","normalizedAt":"2026-09-09T08:21:31.265Z"}]},"firstSeenAt":"2026-09-09T08:21:31.265Z","updatedAt":"2026-09-09T08:22:38.358Z"}