{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_gzwwrctqr7pd","handle":"logseq-mcp-server","url":"https://wellknown.network/agents/logseq-mcp-server","links":{"self":"https://wellknown.network/agents/logseq-mcp-server/record.json","html":"https://wellknown.network/agents/logseq-mcp-server","markdown":"https://wellknown.network/agents/logseq-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/logseq-mcp-server","status":"https://wellknown.network/api/v1/agents/logseq-mcp-server/status","claim":"https://wellknown.network/agents/logseq-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/logseq-mcp-server/claim.json","badge":"https://wellknown.network/agents/logseq-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/logseq-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/logseq-mcp-server/tools"},"ard":{"identifier":"urn:air::server:logseq-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"logseq-mcp-server","summary":"Read-only MCP server for LogSeq graphs: batched Datalog queries, bounded results, one native binary.","description":"# logseq-mcp-server\n\nA read-only [MCP](https://modelcontextprotocol.io) server for [LogSeq](https://logseq.com) graphs. It gives an AI client 10 tools in four kinds: `get` (a page, a block, what is open now), `find` (blocks and pages by text, link, property or period), `explore` (a page's context, its link network and its timeline) and `check` (a gate on a `[[link]]` pass). It never writes to the graph.\n\nThis package is the server itself: one native Rust binary, with no Python code and no runtime dependencies. It is the same binary, byte for byte, as the one on the project's [GitHub Releases](https://github.com/eborden/logseq-mcp-server/releases). The wheels are built and attested by the release workflow, attached to the release beside the binaries, and uploaded here from there once the release is public.\n\n## Install\n\nWheels exist for macOS (Apple silicon and Intel) and Linux (x86_64, glibc and musl). There is no Windows wheel yet, so installing on Windows fails with \"no matching distribution\".\n\n```bash\nuvx logseq-mcp-server      # run it without installing\nuv tool install logseq-mcp-server\npipx install logseq-mcp-server\n```\n\n## Set up LogSeq\n\n1. In LogSeq, turn on the HTTP API server (Settings, then API) and generate an auth token.\n2. Create `~/.logseq-mcp/config.json`:\n\n   ```json\n   {\n     \"apiUrl\": \"http://127.0.0.1:12315\",\n     \"authToken\": \"your-token-here\"\n   }\n   ```\n\nThe server reads its token from that file, so no credentials go in your client's config.\n\n## Connect a client\n\nClaude Desktop (`claude_desktop_config.json`), or any client that starts MCP servers over stdio:\n\n```json\n{\n  \"mcpServers\": {\n    \"logseq\": {\n      \"command\": \"uvx\",\n      \"args\": [\"logseq-mcp-server\"]\n    }\n  }\n}\n```\n\nClaude Code:\n\n```bash\nclaude mcp add logseq -- uvx logseq-mcp-server\n```\n\n## More\n\nThe tools, the options (`timeoutMs`, `tips`, `LOGSEQ_MCP_CONFIG`), the Claude Code plugin with skills, and the design notes are in the [project README](https://github.com/eborden/logseq-m…","publisher":null,"homepage":"https://github.com/eborden/logseq-mcp-server","repository":"https://github.com/eborden/logseq-mcp-server","version":"2.1.0","license":null,"protocols":["mcp"],"tags":["logseq","mcp","model-context-protocol","knowledge-graph","rust"],"pricing":null,"endpoints":[{"url":"pypi:logseq-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.859,"provenance":"derived"}],"categories":["dev","knowledge"],"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":"logseq-mcp-server","registry":"pypi","observedAt":"2026-11-05T21:26:49.062Z","publishedAt":"2026-10-16T17:54:02.563733Z","latestVersion":"2.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"logseq-mcp-server","url":"https://pypi.org/project/logseq-mcp-server/","firstSeenAt":"2026-10-12T14:24:54.856Z","fetchedAt":"2026-11-05T21:26:13.935Z","normalizedAt":"2026-11-05T21:26:13.935Z"}]},"firstSeenAt":"2026-10-12T14:24:54.856Z","updatedAt":"2026-11-05T21:26:49.062Z"}