Quipu MCP server
Local knowledge graph memory for agents. SHACL rules refuse bad facts; SPARQL and time travel.
2 stars
Reviews
Write oneNobody has reviewed Quipu yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Quipu tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- –Code scanpackage could not be scannedn/a
- –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 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
What the publisher says
From the Quipu repository's README, as published. We do not edit it. Read it on GitHub
quipu
🪢 A memory for your agents that refuses facts that break your rules
Quipu is a knowledge graph for AI coding agents and the people who run them. It stores what your agents learn as facts, checks every write against rules you declare (SHACL shapes), and refuses the facts that break them, so bad knowledge never gets in. It keeps every version of every fact, so you can ask what was true last Tuesday, and it answers standard SPARQL 1.1. It comes as a command-line tool, a REST server, and a Rust library, and agents reach it through bobbin's MCP server.
A quipu is the Andean knotted-cord record: cords are entities, knots are facts.
Why you would want it
fails with the rule it broke, so an agent can correct it on the spot.
- Bad facts are refused, not cleaned up later. A write that breaks a shape
it was true, so you can query the graph as it was at any moment.
- Nothing is overwritten. Every fact carries when it was recorded and when
1.1 Query, Update, Protocol and Results tests, scored alongside other stores in the conformance report.
- Standard, and measured. It passes all Working Group–approved W3C SPARQL
The long form (sharing between stores, the feature list, the architecture and a comparison): Why Quipu.
Install
Linux x86_64: download the checksummed release.
V=0.8.1
curl -fsSLO "https://github.com/scbrown/quipu/releases/download/quipu-ai-v$V/quipu-quipu-ai-v$V-x86_64-unknown-linux-gnu.tar.gz"
curl -fsSLO "https://github.com/scbrown/quipu/releases/download/quipu-ai-v$V/quipu-quipu-ai-v$V-x86_64-unknown-linux-gnu.tar.gz.sha256"
sha256sum -c "quipu-quipu-ai-v$V-x86_64-unknown-linux-gnu.tar.gz.sha256"
tar -xzf "quipu-quipu-ai-v$V-x86_64-unknown-linux-gnu.tar.gz"
mkdir -p ~/.local/bin
install -m 755 "quipu-quipu-ai-v$V-x86_64-unknown-linux-gnu/quipu" \
"quipu-quipu-ai-v$V-x86_64-unknown-linux-gnu/quipu-server" ~/.local/bin/Anywhere else, build from source (needs a Rust toolchain):
cargo install quipu-ai --locked --features fullThe crate is quipu-ai; it installs quipu and quipu-server, plus two test utilities (quipu-shacl-conformance, seed-fixtures) you can ignore. Check it:
quipu --versionquipu 0.8.1If that prints an older version, another copy is earlier on your PATH: which -a quipu.
First success in three commands
Write a rule (every Person needs a name), two people who follow it, and one who does not:
mkdir quipu-demo && cd quipu-demo
printf '@prefix sh: <http://www.w3.org/ns/shacl#> .\n@prefix ex: <http://example.org/> .\nex:PersonShape a sh:NodeShape ; sh:targetClass ex:Person ;\n sh:property [ sh:path ex:name ; sh:minCount 1 ] .\n' > shapes.ttl
printf '@prefix ex: <http://example.org/> .\nex:alice a ex:Person ; ex:name "Alice" ; ex:knows ex:bob .\nex:bob a ex:Person ; ex:name "Bob" .\n' > people.ttl
printf '@prefix ex: <http://example.org/> .\nex:carol a ex:Person .\n' > carol.ttlThen load the good facts, ask a question, and try the bad one:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
claude mcp add quipu -- docker run -i --rm ghcr.io/scbrown/quipu:0.9.0
Quipu: common questions
- Is Quipu MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the Quipu safety report
- How do I install Quipu?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Quipu need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Quipu maintained?
- The last commit was in the last day (2026-09-26). The latest release is v0.9.0.
- What can I use instead of Quipu?
- Servers from other publishers that do the same job: ReasonGraph Cloud memory MCP server, travel.art MCP server and Argon MCP server. Compare all Quipu alternatives.
Alternatives to Quipu
Same job from other publishers: the closest match first, then the best rated.
- ReasonGraph Cloud memoryGraph memory for AI agents: entities, cause-effect links, cross-session recall, time travel.not reviewedGrowingA
travel.artArt-tourism data for AI agents: biennales, art fairs, museums, layover itineraries with 2026 facts.not reviewedGrowingA- ArgonVersioned MongoDB sandboxes for AI agents: branch, time-travel, merge, and undo over MCP.not reviewedEstablishedB
- AgentmapThe TS/JS-accurate repo map for coding agents: ts-morph import/symbol/call graph + MCP query toolsnot reviewedGrowingA
- Repo GraphStructural graph map of any codebase so LLMs navigate by structure, not guesswork.not reviewedGrowingA