{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_g63fgfdj6j7k","handle":"precis-mcp","url":"https://wellknown.network/agents/precis-mcp","links":{"self":"https://wellknown.network/agents/precis-mcp/record.json","html":"https://wellknown.network/agents/precis-mcp","markdown":"https://wellknown.network/agents/precis-mcp/record.md","api":"https://wellknown.network/api/v1/agents/precis-mcp","status":"https://wellknown.network/api/v1/agents/precis-mcp/status","claim":"https://wellknown.network/agents/precis-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/precis-mcp/claim.json","badge":"https://wellknown.network/agents/precis-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:precis-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"precis-mcp","summary":"MCP server giving LLM agents a seven-verb API over papers, documents, code, personal state, patents, and cached web/Wolfram/YouTube tool calls — backed by PostgreSQL + pgvector","description":"# precis-mcp\n\n[![check](https://github.com/retospect/precis-mcp/actions/workflows/check.yml/badge.svg)](https://github.com/retospect/precis-mcp/actions/workflows/check.yml)\n[![PyPI](https://img.shields.io/pypi/v/precis-mcp.svg)](https://pypi.org/project/precis-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/precis-mcp.svg)](https://pypi.org/project/precis-mcp/)\n[![License](https://img.shields.io/github/license/retospect/precis-mcp.svg)](LICENSE)\n\nA [Model Context Protocol](https://modelcontextprotocol.io/) server that\ngives language-model agents a small, uniform API for reading, writing,\nand searching across papers, documents, personal state, code, and\ncached tool calls. Small-model-friendly (7B-class agents are the design\ntarget); stores content in PostgreSQL with `pgvector`.\n\n> **Status.** v8.0.0 — ground-up redesign of v1. Twenty-two kinds\n> shipping across ref / tool / discovery categories, seven verbs,\n> plugin surface stable. The discovery layer (persistent\n> per-segment keywords + per-sentence embeddings) and the\n> verifier-workflow `citation` kind landed 2026-05-31; see\n> [`docs/design/storage-v2.md § Discovery layer`](docs/design/storage-v2.md).\n> v5.2.6 on PyPI is the last v1-line release;\n> see [`CHANGELOG.md`](CHANGELOG.md) for the migration path.\n\n## What it does\n\nOne tool surface — **seven verbs** discriminated by a single `kind=`\nargument — over three categories of content:\n\n- **Ref kinds** (content addressed by slug or integer id): `paper`,\n  `skill`, `oracle`, `quest`, `conv`, `markdown`, `plaintext`,\n  `python`, `todo`, `memory`, `gripe`, `fc` (flashcard),\n  `citation` (verified claim → source quote).\n- **Tool kinds** (stateless or cache-backed; pass `q=` or `id=`, get\n  text back): `calc`, `math` (Wolfram), `youtube`, `web` (fetch +\n  search + bookmark), `websearch` / `think` / `research` (Perplexity\n  Sonar tiers), `patent` (EPO OPS).\n- **Discovery kind**: `random` — pick a random indexed block to\n  stumble into content when you don't kn…","publisher":null,"homepage":"https://github.com/retospect/precis-mcp","repository":"https://github.com/retospect/precis-mcp","version":"8.4.3","license":null,"protocols":["mcp"],"tags":["agent-tools","ai-agent","ast","callgraph","claude","code-navigation","context-management","cursor","docx","latex","llm","markdown","mcp","mcp-server","model-context-protocol","patents","pdf","perplexity","pgvector","postgres","progressive-disclosure","python","scientific-papers","semantic-search","spaced-repetition","token-optimization","windsurf","wolfram-alpha","youtube-transcripts"],"pricing":null,"endpoints":[{"url":"pypi:precis-mcp","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":"data.database","name":"Databases","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"research.academic","name":"Academic Research","confidence":1,"provenance":"derived"},{"slug":"documents.conversion","name":"Document Conversion","confidence":1,"provenance":"declared"},{"slug":"productivity.tasks","name":"Tasks & To-do","confidence":0.745,"provenance":"derived"}],"categories":["data","documents","productivity","research"],"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":"precis-mcp","registry":"pypi","observedAt":"2026-09-10T10:25:34.927Z","publishedAt":"2026-06-05T19:22:12.398436Z","latestVersion":"8.4.3"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"precis-mcp","url":"https://pypi.org/project/precis-mcp/","firstSeenAt":"2026-09-10T10:23:48.105Z","fetchedAt":"2026-09-10T10:23:48.105Z","normalizedAt":"2026-09-10T10:23:48.105Z"}]},"firstSeenAt":"2026-09-10T10:23:48.105Z","updatedAt":"2026-09-10T10:25:34.927Z"}