MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Find where your notes disagree — contradiction detection for markdown vaults.
pypi MIT -
contradiction-mcpactive
Production-quality MCP server for detecting conflicting and inconsistent information across connected sources
npm MIT -
Autonomous Model Context Protocol (MCP) engine for factual consistency, version reconciliation, and conflict resolution across engineering knowledge bases.
MIT ★ 10 -
Catch logic contradictions in AI prompts, rules, and compliance policies — deterministic truth table engine with MCP, CLI, and NL support
pypi AGPL-3.0-only -
patha-memorygithub.com/autotelicbydesign/pathaupdated this year
Local-first AI memory with contradiction detection, non-destructive supersession, and empirically non-commutative belief evolution. Plugs into any MCP-compatible AI tool.
pypi Apache-2.0 -
MCP server for TIMPS — persistent memory, contradiction detection, bug patterns, burnout monitoring, and 69 tools for Claude Code, Cursor, and Windsurf
npm MIT -
knowledge-agentgithub.com/oladri-renuka/knowledge-agentupdated this year
Persistent belief graph from document sequences. Extracts entities/claims, resolves duplicates via two-pass entity resolution (alias + cosine similarity), detects contradictions across sources, answers questions with citations. 936 entities from 173 pages using 9 API calls. MCP server for Claude Desktop/Cursor.
-
io.github.frankchu91/mindbasegithub.com/frankchu91/mindbaseno update data
LLM-maintained personal wiki: cross-references sources, flags contradictions. Local markdown.
npm -
io.github.mifactory-bot/mifactory-logic-verifiergithub.com/mifactory-bot/mifactory-logic-verifierno update data
Verify AI agent reasoning and logic for errors and contradictions. Pay-per-use.
npm -
Local explanation of reproducibility signals and toolchain contradictions without exact versions or secret values
npm MIT -
purpl_braingithub.com/skalrn/purpl_brainupdated this year
Shared decision memory for multi-agent codebases - contradiction detection, cross-session retrieval, MCP interface
MIT -
groomingnatorgithub.com/ibalashov-srb/groomingnatorupdated this year
Claude Code MCP plugin for structured grooming sessions. Analyzes inputs in real-time, surfacing gaps, contradictions, and edge cases.
npm MIT -
A claims memory for agents: assert beliefs, let them decay, surface contradictions (MCP + CLI)
npm MIT -
promptlint-mcpgithub.com/sean-sunagaku/promptlint-mcpupdated this year
Static linter for AI prompts — catch contradictions, strip fluff, save tokens. CLI + MCP server.
npm MIT ★ 1 -
gnokeegithub.com/omurlabs/gnokeeupdated this year
Memory infrastructure for personal AI — bi-temporal facts, honest contradictions, autonomous maintenance, real forgetting. MCP-native, multi-tenant, multilingual.
pypi Apache-2.0 -
memmd-mcpgithub.com/matamong/memmd-mcpupdated this year
A shared memory layer for AI agents — one memory.md synced across Claude Desktop, Cursor, Claude Code, and any MCP client. Auto-deduplication, contradiction resolution, and stale cleanup included.
pypi MIT ★ 2 -
@tinydarkforge/codicilgithub.com/tinydarkforge/codicilupdated this year
Local-first memory and assertion ledger for AI coding agents. Confidence-weighted, contradiction-aware, token-budgeted context over MCP.
npm MIT -
MCP prototype that checks agent memory for stale facts, contradictions, secrets and missing evidence using Cognee.
MIT ★ 4 -
smalltalk-cligithub.com/apexautomate/smalltalkupdated this year
Institutional memory for AI agents. Structured decisions, contradiction detection, per-response drift prevention, and a compounding PAG loop. 25 MCP tools. Zero infrastructure.
pypi MIT -
SCM_OpenSourcegithub.com/clyrai/SCM_OpenSourceupdated this year
SCM Memory: embedded lifecycle memory for AI agents, with consolidation, contradiction handling, forgetting, and wake summaries.
MIT -
Checks every claim in a coding agent's "done" message against what actually ran: backed, contradicted or never ran. Web app and MCP server.
MIT -
Forge app for Jira and Confluence: catches work that contradicts team decisions, with a Rovo agent, MCP server and Teamwork Graph blast radius. Codegeist 2026.
MIT -
A human-gated trusted memory ledger for agent systems, with scoped claims, provenance, contradictions, and supersession.
Apache-2.0 ★ 3 -
sendimentgithub.com/leonwangg1/sendimentupdated this year
MCP server giving AI agents persistent, self-cleaning memory across sessions. Forgets the stale, merges duplicates, resolves contradictions.
MIT ★ 2 -
ccsp-mcpupdated this year
ISI MCP Server — Persistent AI Identity Infrastructure powered by CCSP. Session lifecycle, contradiction detection, grounding verification, behavioral signature computation, and identity flywheel.
npm MIT -
@lazymac/prompt-lint-mcpupdated this year
ESLint-style static analysis for LLM prompts. Detects ambiguous instructions, contradicting rules, missing examples, token waste, role confusion, and more — before you spend a single API call.
npm MIT -
gnokeegithub.com/gnokeelabs/gnokeeupdated this year
Memory infrastructure for personal AI — bi-temporal facts, honest contradictions, autonomous maintenance, real forgetting. MCP-native, multi-tenant, multilingual. Placeholder release; see https://github.com/gnokeelabs/gnokee.
npm Apache-2.0 -
Governed persistent memory for AI agents — trust scoring, contradiction detection, and belief lifecycle management via MCP and API
NOASSERTION ★ 3 -
cortex-memgithub.com/Aravindargutus/cortex-memupdated this year
Cortex — persistent AI memory for Claude Desktop & Claude Code. Local MCP server with a typed knowledge graph, contradiction detection & background scheduler. 20/20 benchmark, 27/27 edge cases, zero API keys.
npm MIT -
evidencechaingithub.com/tejasprasad2008-afk/evidencechainupdated this year
Autonomous forensic investigation agent with self-correction for SANS SIFT Workstation. 21 typed MCP tools, 7 contradiction detectors, evidence-weighted confidence scoring. Built for SANS Find Evil! Hackathon.
MIT -
@sheaf-labs/mcpactive
Sheaf MCP server — a coherence gate for AI agents. Route a consequential action through Sheaf before it runs; a contradiction among the minds parks it for human release.
npm UNLICENSED -
Source-cited research agent for developers: asks SerpApi (Google, News, Scholar, GitHub/PyPI pages), cross-checks sources, returns a cited brief with contradiction flags.
MIT -
The AI memory layer with 17 intelligence tools — catches contradictions, predicts burnout, tracks relationships. Model-agnostic, self-hosted
npm MIT ★ 6 -
reponoesisgithub.com/MathewAddala/reponoesisupdated this year
Local, zero-cost semantic change propagation and logic contradiction check for AI coding agents. Cryptographic Merkle linking + stdio Model Context Protocol (MCP) server.
MIT ★ 1 -
Cognitive-Bridgegithub.com/JosephOIbrahim/Cognitive-Bridgeupdated this year
An MCP server that gives AI a compositional mind — persistent memory that catches contradictions, built on USD LIVRPS composition semantics and mechanically verified against them.
★ 1 -
Your AI already wrote this. Decision memory + enforcement for AI-assisted codebases — mine decisions from Claude Code/Cursor sessions, inject them into every agent's context, block contradictions and duplicates. Local, free, MCP.
Apache-2.0 ★ 1 -
kontrol-freek-mcpgithub.com/berkbayri/kontrol-freek-mcpupdated this year
AI assumption firewall for MCP agents — intercepts risky decisions, checks past decisions, detects contradictions, and gates human approval via Telegram or Slack.
pypi ★ 1 -
Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, and fades stale memories via temporal decay, written in Rust (Apache-2.0) as a library, MCP server, or HTTP cluster.
cargo Apache-2.0 ★ 180 -
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.
npm Apache-2.0 ★ 30 -
Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware retrieval.
go Apache-2.0 ★ 50 -
Git-backed project memory for AI coding agents: claims as reviewed markdown in your repo, anchored to the code they describe, with drift detection, supersede chains and a CI contradiction gate for shared stores.
MIT ★ 10 -
internet-context-mcpgithub.com/vivekvar-dl/internet-context-mcpupdated this year
Read-only MCP server giving AI agents the web as compact, ranked, verified evidence. Local cross-encoder reranker, NLI claim verification, semantic cross-source agreement and contradiction detection. No API keys.
npm MIT ★ 1 -
🛡️ Make AI interrupt itself and challenge your thinking. Turns Claude into a philosophical sparring partner who actively contradicts comfortable conversations and challenges confirmation bias.
npm MIT -
The system of record for what an AI agent believed and did. Append-only beliefs with evidence, contradictions kept, risky actions gated behind a named human. MIT, self-hosted.
npm MIT -
Scale parallelism. Preserve alignment. A fleet of coding agents builds one task in parallel against a spec contract; a decision that contradicts one already in force is refused — deterministically, no model in the decision path.
npm MIT -
Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, and Windsurf with temporal decay, contradiction detection, a knowledge graph, and autonomous consolidation, backed by the YantrikDB Rust engine.
pypi MIT ★ 25 -
Persistent local memory for Claude, Cursor & Codex. 21 MCP tools, hybrid retrieval (BM25 + vector RRF), bi-temporal queries, contradiction detection. SQLite + Knowledge Graph. No cloud, no API keys. npx @studiomeyer/local-memory-mcp
npm MIT ★ 16 -
Use when an AI agent is about to state a companys name, number or status: one MCP tool that checks each claim against the company registers and returns supported, contradicted, stale or not_checkable with the registers own value and date.
MIT -
Relay: shared, time-aware graph memory for teams of AI agents, built on FalkorDB. The agents never message each other, yet never contradict each other. Live demo: WiFight, an AI ISP support desk. Graph Hacks 2026 · Track 02: Agent Memory & Coordination
MIT -
better-ctxgithub.com/jadzeino/betterctx-clientupdated this year
Context Intelligence Engine with CCP. 34 MCP tools, 8 read modes, 90+ compression patterns, cross-session memory (CCP), persistent AI knowledge with temporal facts + contradiction detection, multi-agent context sharing + diaries, LITM-aware positioning, AAAK compact format, adaptive compression with Thompson Sampling bandits. Supports 24 AI tools. Reduces LLM token consumption by up to 99%.
cargo MIT -
memogithub.com/jagoff/memoactive
Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.
pypi MIT ★ 27 -
Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over stdio against a local SQLite store. Drop-in for the MCP reference memory server. Every memory keeps its source, who may read it, and the evidence that contradicts it.
npm Apache-2.0 ★ 16 -
MCP server for verifying AI agent claims vs reality — inline grounding-check on retrieval context, swallowed-exception scanner on agent-written code, and multi-turn transcript review for unverified completions + cross-turn contradictions. Sub-second, local, free, MCP-native — the lightweight complement to dashboard-based eval frameworks (DeepEval, Phoenix, LangSmith).
pypi MIT License -
sigma-guardgithub.com/invariant-research/sigma-guardupdated this year
Deterministic structural verification for knowledge graphs, agent state, and LLM output using sheaf cohomology. MCP server included.
pypi BSL-1.1