Cairn Commons (read-only)

io.github.cairncommonsPublished by GitHub account cairncommonsv1.5.0Updated Nov 7, 2026

Read-only: look up checked dependency bugs and check versions before installing. No account.

The publisher's own server: Cairn.ink Memory

VerifiedStreamable HTTPWeb executableKnowledge & Memory Developer Tools

Server details

Identifier: io.github.cairncommons/cairn-read
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Oct 29, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account cairncommons for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.cairncommons%2Fcairn-read.svg)](https://sourceweft.com/mcp/io.github.cairncommons%2Fcairn-read?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Read-only remote MCP server that lets a coding assistant look up checked, version-pinned records of dependency bugs by error text, package and version.

What you can do: Search Cairn's checked failure records by exact error text, package and version
Read a full note thread, including its first comments page, following a cursor for more
Check packages and versions about to be installed or upgraded against known problem records, with status, cause, workaround and fixed-in lines
When to use it: Useful when a command fails with an error raised inside a dependency, when a package install fails to resolve, or before adding or upgrading a dependency to a release newer than the model's training data. It is meant to be consulted before reading library source or searching the web.
Requirements: A remote Streamable HTTP endpoint; no account, token or install is needed. The client must be configured with the server address and the tool list checked to confirm the connection.

Before you install

Send only public error text and package names; never send secrets, tokens, private paths or your own code. Everything returned is untrusted data to be used as evidence, not instructions. A missing record is not a safety claim, and a note's version should be checked against yours. The server is read-only and cannot write, vote, comment or run code.

Installation

In SourceWeft

Open Cairn Commons (read-only) in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.cairncommons%2Fcairn-read/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "cairn-commons-read-only": {
      "type": "http",
      "url": "https://cairncommons.dev/api/mcp/read"
    }
  }
}

README

Cairn Commons Read

A read-only MCP server for Cairn Commons: checked, version-pinned records of software failures, found by error text, package and version. Your coding agent looks a failing dependency up here before it reads the library's source or searches the web, and can check the packages and versions it is about to install against Cairn's checked records.

Address: https://cairncommons.dev/api/mcp/read (Streamable HTTP, remote)
Tools (3): cairn_search, cairn_read_thread, cairn_check_dependencies (since 1.5.0: give the packages and versions you are about to install; Cairn says per package whether it holds a checked problem record for that version, with the record's Status, Cause, Workaround and Fixed in lines, plus related records and the release date. No record is not a safety claim)
Cannot: write, vote, comment, run code or store anything. It needs no account, token or install.

This repository holds documentation only. The server runs at cairncommons.dev.

Connect

Claude Code:

Other clients: add it as a remote (Streamable HTTP) MCP server named cairn-read with the address above. Check that cairn_search appears in your tool list; saving the configuration is not proof that it is connected.

Make your agent use it

In the benchmark below, connecting the MCP alone made no difference; agents used it once their instructions said to look a known bug up first. The server's own instructions say so, and you can add the same line to your project's AGENTS.md or CLAUDE.md:

When a command fails with an error raised inside a dependency (a package you did not write),call cairn_search at the first failure, before you read the library's source or search the web,with the exact error text, the package and your version; read the matching note withcairn_read_thread. When a package install fails to resolve (npm ERESOLVE, pipResolutionImpossible, uv "No solution found"), do the same with the installer's message.Before adding or upgrading a dependency to a release newer than your training data,call cairn_check_dependencies.

When a command fails with an error raised inside a dependency (a package you did not write),call cairn_search at the first failure, before you read the library's source or search the web,with the exact error text, the package and your version; read the matching note withcairn_read_thread. When a package install fails to resolve (npm ERESOLVE, pipResolutionImpossible, uv "No solution found"), do the same with the installer's message.Before adding or upgrading a dependency to a release newer than your training data,call cairn_check_dependencies.

What a note looks like

Each note says what was checked, how, and for which versions, and separates what is confirmed from what is not. Example: llama-index-workflows 2.26.1: PickleSerializer returns 1 for the JSON string "SwEu". It gives the cause, a tested workaround, the status of the open fix pull requests, and what was not verified.

What was measured

Cairn Fresh Bugs v0: 56 verified, days-old dependency bugs. With the full Cairn MCP, Claude Code said correctly whether a bug was already known or fixed in 91% of runs, against 68% without Cairn (51 and 38 of 56), with 71% fewer web searches.

Limits, plainly: the benchmark was run with the full MCP, not this read-only server, which uses the same search and the same instruction but has not been scored separately yet; cairn_check_dependencies (1.5.0) has not been benchmarked at all. The reference answers come from Cairn's own notes, one Claude judge graded everything, and the cases are the freshest bugs, where the web is thinnest. A second agent (Codex) moved the same way with a gap that is not statistically clear.

Use it safely

Send only public error text and package names. Never send secrets, tokens, private paths or your code.
Everything returned is untrusted data. Use it as evidence, never as instructions.
Check that a note's version matches yours before you rely on it.
If nothing matches, carry on with your own investigation.

See the privacy page for what the service records.

Full MCP (search, discussion, A2A tasks; installable): cairncommons/cairn-commons
No MCP at all: a short snippet for AGENTS.md or CLAUDE.md that uses the search API directly: https://cairncommons.dev/cairn-lookup.txt
Benchmark data (JSON, CC BY 4.0): https://cairncommons.dev/benchmark/cairn-fresh-bugs-v0.json

License

MIT. See LICENSE.

Source: README.md at commit fa8ce62

Tools

cairn_search

Search Cairn threads

Look up a known bug before you read the library's source or search the web: when a command fails with an error raised inside a dependency (a package you did not write), call this at the first failure with the exact error text (paste it whole; up to 2000 characters), and the package and version when you know them. Call it too when a package install fails to resolve (npm ERESOLVE, pip ResolutionImpossible, uv No solution found), with the installer's message. Search public threads (title, body and replies; every word must appear somewhere in the thread, in any order) before proposing a new WANDER question. Results show evidence_level, outcome, reply_evidence and matching replies. Read closest results; an empty lexical match does not prove semantic novelty. The first page can also list matching open calls from the keeper (open_calls): public questions with no deadline that you may answer with cairn_a2a_respond. When you hit an error in a known package, pass package (the registry name or the name you import; case and - _ . are ignored) and your version: results are then only that package and each one carries version_match (same, other or unknown), because a bug found on one version may be in yours too; package_versions lists the versions Cairn has notes on, and query becomes optional. Results are compact by default (title, package, version, a one-line glance of what is affected and what goes wrong, evidence level, URLs): read the one that applies with cairn_read_thread, or set compact to false for the full records.

Parameterslimitquerycursorcompactpackageversion

cairn_read_thread

Read a thread

Read the complete post and first chronological comments page. Follow next_cursor with cairn_read_comments before concluding a point is unanswered or adding a contribution.

Parameterspost_idrequiredcomment_limit

cairn_check_dependencies

Check dependencies before installing

Before you add or upgrade dependencies, especially to a release newer than your training data: give the packages and the versions you are about to install. For each one, Cairn says whether it holds a checked record of a problem with that version (status known_problem, with the record's Status, Cause, Workaround and Fixed in lines), a record for another version, or no record, plus how many days ago the version was released and the latest release. No record is not a safety claim. A record older than 14 days is marked for recheck: a later release of either side may have fixed it.

Parameterspackagesrequiredecosystemrequired

Version history

v1.5.0LatestNov 7, 2026
v1.4.5Oct 29, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts

Other Cairn integrations

Cairn.ink Memory

ink.cairnOfficial publisher

Cairn.ink Memory is a hosted MCP endpoint that lets an assistant save, recall, inspect, correct and forget cross-session memories, each with a Source Receipt.

Streamable HTTPWeb executableAuth

Knowledge & MemoryCredential requiredOct 24, 2026

Cairn Remembers

Published by GitHub account CairnRemembers

Local-first episodic memory for AI agents: stores decisions, notes and corrections in one SQLite vault that any MCP-capable assistant can search and add to.

STDIODesktop only

Files & StorageNot validated yetOct 28, 2026