MCP.Market

World Model MCP server

by SaravananJaichandar·io.github.SaravananJaichandar/world-model-mcp·v0.15.5·22 stars
No reviews yet

Temporal knowledge graph for codebases with constraint enforcement at the edit boundary.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

22 stars101 downloads/wk

Reviews

Write one

Nobody has reviewed World Model yet.

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

World Model tools (27)

write = sends, deletes, buys or posts

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

  • export_claude_md

    Generate a CLAUDE.md document from the knowledge graph (top constraints, recent decisions, known bug regions, co-edit patterns).

  • find_contradictions

    Find pairs of facts that contradict each other based on similarity and status differences

  • get_agents_md_constraints

    Parse AGENTS.md / CLAUDE.md / GEMINI.md / .agents/skills/*.md in the project and return declarative constraints. Mixed into PreToolUse enforcement automatically; this tool exposes the same data for inspection.

  • get_co_edit_suggestions

    Get files commonly edited alongside the given file based on historical patterns

  • get_compaction_audit

    List recent compaction audit entries, most-recent first. Filter by session_id or limit count.

  • get_constraints

    Get constraints (linting rules, patterns, conventions) for a file

  • get_context_for_action

    Pre-action context bundle: constraints, decisions, bugs, co-edits, related facts, and risk score for a file before editing

  • get_decision_log

    Get decision traces showing agent proposals and human corrections

  • get_health_report

    Memory health diagnostics: orphans, stale facts, contradictions, decay candidates, DB sizes

  • get_injection_context

    Return a compact constraint+fact bundle for PostCompact / UserPromptSubmit hooks to re-inject after context loss.

  • get_related_bugs

    Get bugs fixed in a file and assess regression risk

  • ingest_pr_reviews

    Pull GitHub PR review comments and convert them into learned constraints in the knowledge graph

  • predict_regression

    Score regression risk for a proposed change to a file based on past bugs, test failures, and constraint violations

  • predict_test_failures

    Surface tests likely to fail given a set of edited files

  • promote_constraint

    Promote a constraint from this project to all other registered projects

  • query_fact

    Query the knowledge graph for facts about entities (APIs, functions, classes, etc.)

  • recall_transcript_range

    Hydrate a Claude Code session transcript by line range. Lets agents trace a fact back to the exact conversation that produced it.

  • record_compaction_audit

    Record a context-compaction event with token counts and what was re-injected. Lets developers audit what was remembered across compaction boundaries.

  • record_correction

    Record a user correction to Claude's output (high-priority learning signal)

  • record_decision

    Record a decision trace: what the agent proposed and how the human responded

  • record_event

    Record a development event (file edit, test run, etc.)

  • record_test_outcome

    Record test results and link failures to recent code changes

  • resolve_contradiction

    Pick a winner between two contradicting facts using a confidence-weighted strategy (auto, keep_higher_confidence, keep_most_recent, keep_most_sources, supersede_a, supersede_b, manual).

  • search_global

    Search entities across all registered world-model projects

  • seed_project

    Scan the project codebase and populate the knowledge graph with entities and relationships from existing code

  • simulate_change

    Project blast radius and historical outcomes for a proposed change

  • validate_change

    Validate a proposed code change against known constraints

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan92 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 10 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How World Model compares

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

Safety score
83/100
higher than 68% of 4,460 AI and agents servers
Tools
27
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
22
more than 90% of 2,711 AI and agents servers
Downloads a week
101
more than 64% of 1,538 AI and agents servers with a package

What its tools let an agent do: 27 read

Install World Model in Claude Code, Cursor or VS Code

claude mcp add world-model-mcp -- uvx world-model-mcp
Add to Cursor

What the publisher says

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

World Model MCP

Persistent memory + optional signed audit for AI coding agents.

world-model-mcp is persistent memory plus a post-quantum-signed, offline-verifiable audit trail for AI coding agents (FIPS 205 hybrid Ed25519 + SLH-DSA), MIT-licensed and fully local.

world-model-mcp ships a local SQLite knowledge graph your agent queries every turn: hallucinations become verifiable, corrections stick across sessions, and regressions get caught before they land. Flip on the audit chain and every event is signed with FIPS 205 hybrid Ed25519 + SLH-DSA, verifiable offline forever. MIT-licensed, runs entirely local, works with 10+ AI coding agents including Claude Code, Cursor, Codex, Continue, Cline, Windsurf, GitHub Copilot Chat, pi, OpenClaw, and Hermes Agent.

Latest: v0.16.3. Metadata refresh. No code changes. The PyPI summary and keyword set now name both artifacts that ship in this wheel: the MCP world-model memory server for coding agents, and the etch-verify offline audit-chain verifier CLI. Both were already installed by every prior release; the metadata is now honest about that so a searcher looking for an offline audit-chain verifier can find the package. v0.16.2 shipped CI hardening plus the world-model demo live notary beat introduced in v0.16.0 (three sample decisions signed into a real hybrid-signed epoch, verified VALID, mutated one byte to prove tamper detection fires live, then restored). Full version history in CHANGELOG.md.

Try it in 10 seconds

pip install -U world-model-mcp && world-model demo

You will see three sample decisions signed into a tamper-evident epoch, then the demo mutates one byte and re-verifies to prove the tamper is detected instantly (INVALID), then restores and re-verifies (VALID again). Offline, no account, no network. A world-model-demo-receipt.json lands in your current directory and a shareable etch.systems/verify#… URL is printed for anyone to check the same receipt in a browser.

mcp-name: io.github.SaravananJaichandar/world-model-mcp

Prefer a managed hosted version?

If you want the same signed audit chain without running the OSS server yourself, etch.systems ships a managed variant that uses this package as its offline reference verifier.

  • No infrastructure to run (POST your first event in 30 seconds, no signup)
  • Compliance framework mapping to SR 11-7, EU AI Act Article 12, ISO 42001, NIST AI RMF, SOC 2 CC7
  • External anchoring shipped end-to-end (Sigstore Rekor + Bitcoin OpenTimestamps)
  • Portable per-agent identity with key rotation and delegation across MCP client tools (Claude Code, Cursor, Continue, Cline, Codex)
  • Offline verifier stays the same: pip install world-model-mcp && etch-verify manifest.json verifies the hosted chain against pinned public keys without depending on the hosted service being online
curl -X POST https://etch.systems/v1/your-project

Returns a bearer token and an MCP endpoint you can point any MCP-compatible client at. Full docs at etch.systems.

FAQ

Shortened. The full README is on GitHub.

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

World Model: common questions

Is World Model MCP server safe?
Mostly: it is graded B (83/100). Read the World Model safety report
How do I install World Model?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does World Model need an API key?
Yes. The registry entry asks for ANTHROPIC_API_KEY.
Is World Model maintained?
The last commit was 50 days ago (2026-09-15). The latest release is v0.15.5.
What can I use instead of World Model?
Servers from other publishers that do the same job: Total Agent Memory MCP server, Basic Memory MCP server and Agent-Native Slides MCP server.
How does World Model compare with other AI and agents MCP servers?
safety score 83/100 (higher than 68% of 4,460 AI and agents servers); tools 27 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to World Model

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

  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Agent-Native Slides
    Agent-Native Google Slides - generate and edit React presentations
    More from BuilderIO →
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A