MCP.Market

Compendio MCP server

by RuloGB·io.github.RuloGB/compendio-mcp·v1.7.2·5 stars
No reviews yet

Indexes your project's markdown docs and serves them to any agent via local hybrid search.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

5 stars106 downloads/wk

Reviews

Write one

Nobody has reviewed Compendio yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Compendio tools (3)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • docs_overview

    Map of the documentation corpus: counts by type and module, plus one line per document

  • read_doc

    Reads one section of a document, along with its frontmatter. Built for sections, not

  • search_docs

    Hybrid search (lexical BM25 + semantic) in natural language over the project's

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan101 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 25 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Compendio compares

Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 1,299 Productivity servers
Tools
3
the typical Productivity server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
5
more than 70% of 854 Productivity servers
Downloads a week
106
more than 58% of 427 Productivity servers with a package

What its tools let an agent do: 3 read

Release history: 3 versions in the registry since 2026-09-13, latest 2026-09-20, typically one every 6 days.

Install Compendio in Claude Code, Cursor or VS Code

Runs npx -y compendio-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add compendio-mcp -- npx -y compendio-mcp
Add to Cursor

What the publisher says

From the Compendio repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.RuloGB/compendio-mcp -->

Your project's documentation, served to any agent in the fewest possible tokens. A local RAG retrieval layer exposed as an MCP server. Your agent stops grepping and dumping whole files — it reaches the right paragraph instead.

What it does &bull; Requirements &bull; Quick Start &bull; Configuration &bull; MCP Tools &bull; CLI &bull; How it works &bull; Incremental sync &bull; Multilingual &bull; Full docs

The problem

Your agent doesn't know your documentation. So it does what it can: grep, then cat a 400-line file to answer a question that lived in one paragraph. Three files later the context window is full of noise and the answer is still a guess.

Attaching the whole docs/ folder doesn't fix it — it just moves the waste earlier. Neither does keyword search: nobody writes questions using the exact words the document uses.

Same question, same model, and both answers are correct — the difference is what it cost to get there. 6 tool calls &bull; 29s &bull; 32,301 tokens &nbsp;→&nbsp; 2 tool calls &bull; 12s &bull; 17,684 tokens. Figures read from OpenCode's own elapsed label and cost tooltip, on an 81-document corpus.

What Compendio does

Compendio indexes your markdown documentation and gives any AI agent three tools to find and read exactly what it needs.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19restoreB → Ascore 92

Compendio: common questions

Is Compendio MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Compendio safety report
How do I install Compendio?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Compendio need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Compendio maintained?
The last commit was 44 days ago (2026-09-20). The latest release is v1.7.2.
What can I use instead of Compendio?
Servers from other publishers that do the same job: Exomem MCP server, OrchestKit Docs MCP server and loci MCP server. Compare all Compendio alternatives.
How does Compendio compare with other Productivity MCP servers?
safety score 92/100 (higher than 90% of 1,299 Productivity servers); tools 3 (the typical Productivity server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Compendio

Same job from other publishers: the closest match first, then the best rated.

All Compendio alternatives →
  • Exomem
    Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.
    A
  • OrchestKit Docs MCP
    Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
    A
  • loci
    Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
    A
  • Obsidian Turbocharged
    Governed Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
    B
  • Orbit
    Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
    A