KIP MCP server
io.github.ldclabs/KIP·v1.0.1·85 starsKnowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction.
85 stars
Reviews
Write oneNobody has reviewed KIP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
KIP tools (2, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
execute_kipwrite actionlist_logsList log entries from the KIP backend (if supported). Use this to debug failed executions or inspect recent activity.
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan5 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 qualitystatic API keys via environment variables6/15
- Maintenancelast push 4 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
How KIP compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 85/100
- higher than 70% of 48,255 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 50%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 85
- more than 95% of 28,688 servers
What its tools let an agent do: 1 read · 1 run or deploy
Install KIP in Claude Code, Cursor or VS Code
Runs npx -y @ldclabs/kip-mcp-server on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add KIP -- npx -y @ldclabs/kip-mcp-server
What the publisher says
From the KIP repository's README, as published. We do not edit it. Read it on GitHub
KIP 2.0 — Cognitive State Protocol for Agent Memory
English | 中文
Status
Default development version: KIP 2.0 — normative draft. The repository root contains the current protocol and tooling. KIP v1.0-RC11 is frozen for historical reference and migration; changing the default does not upgrade existing deployments or declare the 2.0 protocol stable.
The 2.0 scope is frozen. This revision made the draft a better memory rather than a larger contract: a world change is one Assertion (temporal succession), coarse dates are time bounds instead of invented instants, preferences change within their kind, a standard policy (kip:memory-default) resolves everyday conflicts the same way on every engine, a Brain can add a relation it meets through the Space's draft vocabulary (DEFINE), retrieval composes with belief in one query (the Search Pattern), and fired Watches reach the business Agent through attention recall. It also took things away: draft packages are not retained (one cognitive-memory@2.0.0), writable caches became computed views, the Cognitive Consistency companion was folded into the Specification, trials and durable workers moved into optional brain/ companions, and the Preference type is gone — a preference is a claim. A second review pass closed the edges of the new semantics: a claim with no stated start began no later than it was made, asserted_at is when the claim was made rather than when it was recorded, two inferences never succeed one another, and the standard policy decides remaining conflicts by recency. See the revision record.
The Rust and Cloudflare Durable Object engines target KIP 2.0 drafts. Their shared suite now lives here as the executable engine suite; both pass every case of the current suite, including the draft vocabulary, supersession scope, computed strength and ingestion batch fixtures (anda-db 985451b), so no fixture is pending_engine. The protocol remains 2.0-draft, independently of tooling versions, and no real Brain learning result is claimed by structural tests.
Start here
- Agent integration: Memory Interface and the Agent memory card.
- Protocol implementation: Specification, syntax reference, and conformance checks.
- Developer tools: TypeScript language toolkit and VS Code extension, both targeting KIP 2.0.
- Existing v1 users: frozen archive, deployment migration, and repository path changes.
The archived MCP server and Skill implement v1 interfaces; native v2 integration starts with the current Interface and wire contracts above.
An interactive version — pan, zoom, relationship tracing, five guided views — is a self-contained file: download it and open it in a browser.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
KIP: common questions
- Is KIP MCP server safe?
- Yes, by our scan: it is graded A (85/100). Read the KIP safety report
- How do I install KIP?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does KIP need an API key?
- Yes. The registry entry asks for
KIP_API_KEY. - Is KIP maintained?
- The last commit was 38 days ago (2026-09-27). The latest release is v1.0.1.
- What can I use instead of KIP?
- Servers from other publishers that do the same job: Codebase Memory MCP server, Neo4j Memory MCP server and State Memory MCP server. Compare all KIP alternatives.
- How does KIP compare with other MCP servers?
- safety score 85/100 (higher than 70% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to KIP
Same job from other publishers: the closest match first, then the best rated.
- Codebase MemoryCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.not reviewedWidely usedC
- Neo4j MemoryMCP Neo4j Knowledge Graph Memory Servernot reviewedEstablishedA
State Memory MCPPersistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.not reviewedEstablishedA