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.
-
blop-mcpgithub.com/n2400813g/blop-mcpupdated this year
MCP-native release confidence control plane for web apps
pypi MIT -
MCP-native release confidence control plane for web apps
★ 1 -
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
Apache-2.0 ★ 9 -
pdfmuxgithub.com/nameetp/pdfmuxupdated this year
Self-healing PDF extraction for RAG — #2 of 8 engines on opendataloader-bench (0.903). Flags pages it can't read instead of dropping them, and certifies any extractor's output for silent drops. Verify signed manifests offline, free. Per-page confidence, 7-tool MCP server, LangChain/LlamaIndex loaders. LlamaParse alternative.
pypi MIT -
Ragnitegithub.com/sunamebr/Ragniteupdated this year
Confidence-Aware RAG Memory Engine for LLMs and coding agents - typed memory (facts, decisions, episodes, code), confidence scoring with answer modes, context packing, semantic caching, hybrid retrieval, MCP server, and Invoke Mode for Claude Code.
MIT -
hypothesis-tracker-mcpgithub.com/mordiaky/hypothesis-tracker-mcpupdated this year
MCP server for persistent hypothesis tracking with Bayesian confidence updates
MIT -
MCP server for agents to explore rust docs, analyze source code, and build with confidence
MIT ★ 142 -
Enhanced MCP server for enabling memory for Claude through a knowledge graph with semantic search, temporal tracking, confidence scores, and entity management
npm MIT -
instinct-mcpgithub.com/yakuphanycl/instinctupdated this year
Self-learning memory for AI coding agents — pattern detection, confidence scoring, auto-promotion via MCP
pypi MIT -
Voice-memo agent with custom MCP servers and least-privilege tools: proposes first, acts only at high confidence, Slack limited to one DM.
★ 1 -
Web search, reading, images, screenshots and multi-wave research — with per-answer confidence
AGPL-3.0 -
Git-style version control for multi-agent shared memory — Provenance Firewall, confidence decay, and cascading rollback (MCP-compatible).
MIT ★ 1 -
AI workflow that turns documents into a confidence-scored knowledge graph with an induced RDFS/OWL ontology
pypi MIT -
spotify-bulk-actions-mcpgithub.com/khglynn/spotify-bulk-actions-mcpupdated this year
MCP server for bulk Spotify operations with confidence-scored song matching, batch playlist creation, and library exports
pypi MIT -
@tocharianou/abuseipdb-mcpgithub.com/tocharianou/abuseipdb-mcpupdated this year
AbuseIPDB MCP Server – IP reputation, abuse confidence scoring, and threat blacklist
npm Apache-2.0 -
MCP server for Laya typed decisions (noul / choice / score): warm model sidecar, token-budget preflight, persisted calibration, honest confidence.
Apache-2.0 ★ 5 -
@mseep/nature-vision-mcpgithub.com/fonkychen/nature-vision-mcpupdated this year
An MCP (Model Context Protocol) server that identifies biological species from images, returning Latin names with confidence scores.
npm -
MCP server: OCR for photographed and scanned Bulgarian documents. Tesseract + OpenCV, per-page confidence, vision fallback only for weak pages, sandboxed to allowed folders.
MIT -
Enhanced MCP server for enabling memory for Claude through a knowledge graph with temporal tracking, confidence scores, and entity management
★ 2 -
@timmeck/trading-braingithub.com/timmeck/brain-ecosystemupdated this year
Adaptive trading intelligence system with Hebbian synapses, spreading activation, Wilson Score confidence, and adaptive calibration
npm MIT -
Compare classifier confidence with accuracy using your own predictions. Browser-based calibration analysis and reports.
MIT -
MCP server for bulk Spotify operations - batch playlist creation with confidence scoring, library exports, CSV imports, and human-in-the-loop review for uncertain matches
MIT ★ 2 -
MCP server for structured AI reasoning — decompose problems into atomic thoughts with dependency graphs, confidence tracking, and interactive D3.js visualization
MIT ★ 95 -
court-notice-gatewaygithub.com/yashpatil582/court-notice-gatewayupdated this year
Ingestion pipeline for US bankruptcy court notices: deterministic phishing gate, LLM extraction with confidence routing, review UI, MCP server
MIT -
MCP server for structured reasoning via Atom of Thoughts — decompose problems into atomic units with confidence tracking and interactive visualization
npm MIT -
Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.
Apache-2.0 ★ 20 -
Date context for AI agents and developers: Chinese lunar calendar, 24 solar terms, holidays and workdays for 12 regions — offline, verified 1900–2100, every answer tagged with its source and confidence.
npm MIT -
Page Finder and Extractorno update data
MCP server for the Mamba Labs Page Finder and Extractor actor on Apify. Company domain in, the named page type located on that company's own website out, with the method that found it and a confidence for that method.
smithery -
Map a domain's public technical footprint with provenance, confidence, and explicit uncertainty. Passive by default, machine-readable, and built to report evidence, not guesses.
Apache-2.0 ★ 5 -
Color Convertgithub.com/bennyzen/mcp-color-convertno update data
Convert colors across formats for seamless design-to-code workflows. Create lighter or darker variants, adjust saturation and hue, and generate palettes, schemes, and full swatch scales. Check contrast for WCAG compliance, pick readable text colors automatically, and validate color inputs with confidence.
smithery -
A Jev-compatible decision layer as an MCP server: typed noul/choice/score questions with probability distributions and confidence. Pluggable backends (local needle/laya models or any OpenAI-compatible endpoint), calibration tracking, conditions v1, eval harness.
MIT -
FactCheck MCP Pack — 6 verification and anti-hallucination tools for any MCP client. Wikipedia checks, source fetch, cross-verification with confidence scoring, Semantic Scholar citations. Keyless and local.
-
MCP server for Laya typed decisions (noul / choice / score): a warm model sidecar, token-budget preflight, and honest confidence. Node entry point for the Python package.
npm Apache-2.0 -
What breaks if I change this file? Import-graph impact analysis for Python and JS/TS over MCP: dependents, affected tests and entry points, cycles, dead-code candidates. Offline, with a confidence line on every answer.
MIT -
hermit-graphgithub.com/kimbapquyenduy/hermit-graphupdated this year
Persistent memory for AI coding agents. Knowledge graph with 4-tier taxonomy, confidence scoring, and MCP protocol support for Claude Code, Cursor, Gemini CLI, Windsurf, Cline, Codex, and OpenCode.
npm MIT -
Movie showtimes across California, Florida and Hawaii over MCP — 56 regional boards, chains, indies, and repertory houses, with source confidence and freshness. Local stdio server, read-only, no API key.
npm MIT -
corroborate-mcpgithub.com/chefcohen/corroborate-mcpupdated this year
Honest claim corroboration for AI agents (MCP server): syndication-aware independent-source counting, confidence scores, and published error rates. Keyless, read-only, open source.
MIT ★ 1 -
aximur-mcpupdated this year
MCP server for the AXIMUR verification API — verify a claim against grounding evidence and get SUPPORTED / UNSUPPORTED / UNCERTAIN with confidence and an audit trail.
npm MIT -
Trace SQL Server tables to C# callers, controller actions, and Razor pages locally. MCP server and CLI with confidence labels. MIT.
MIT -
@1337xcode/cortexgithub.com/1337xcode/cortexupdated this year
Code intelligence MCP server. Indexes your repository into a confidence-aware call graph with SCIP ingestion, framework adapters, and evidence-fusion ranking for AI coding agents.
npm MIT -
Aether-X MCP server — Port Delay Intelligence: calibrated p50/p90 delay confidence intervals and parametric demurrage exposure for global seaports, with a free public feed and no-auth discovery tool.
pypi MIT -
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.
Apache-2.0 ★ 50 -
MCP server + x402 pay-per-call API: signed BUY/SELL/HOLD crypto signals with confidence for Kraken pairs, on-chain track record. USDC on Base, no API keys.
★ 1 -
An MCP client and a retrieval MCP server over a production RAG corpus. Typed responses instead of JSON strings, so a drifting tool schema fails loudly instead of returning a confident wrong answer. 83 tests, 4 ADRs.
MIT -
Genchi MCP connector: project delivery predictions, from the people doing the work, in Claude, ChatGPT and Grok. Ask which projects are heading for a missed deadline and see confidence scores, trends and blockers, with individual votes kept anonymous.
-
trustoraclegithub.com/ToolOracle/trustoracleupdated this year
FeedOracle Trust Layer — Verifiable evidence & verification MCP server for AI agents. 10 tools: claim verification, ES256K-signed facts, provenance tracing, freshness guard, hallucination detection, confidence gates, on-chain evidence anchoring. Standardized verdict schema with proceed/caution/abstain/escalate actions.
NOASSERTION -
Shared, persistent memory for any AI agent. Agents recall what your workspace established — instructions, decisions, facts, preferences, active working threads, and grounded PDF/DOCX/CSV/web documents — before they act, then report outcomes so confidence
npm Apache-2.0 -
scout-intel-mcpgithub.com/omniologynow-rgb/scout-intel-mcpupdated this year
The Google for AI agents — give Claude the power to research any company, analyze competitors, and track market trends. 6 tools, 5+ data sources, confidence-scored JSON. pip install scout-intel-mcp
AGPL-3.0 ★ 2 -
ai-test-failure-analyzergithub.com/aks-builds/ai-test-failure-analyzerupdated this year
8-phase evidence pipeline for Playwright, pytest, Jest, Cypress, Newman, k6, and JUnit failures. Scans git history, application logs, and config to produce confidence-scored root-cause hypotheses. Exposes as MCP server, CLI, and streaming web UI.
★ 1 -
Your design system says one thing, your product ships another. Compare tokens from any design tool (Figma, Sketch, Penpot), live sites & apps, or codebases — get conflicts, confidence scores, and WCAG drift checks. CLI + library + MCP server.
Apache-2.0 ★ 1 -
Memory that abstains instead of guessing: agent memory in a local SQLite file or your own Postgres, with a verdict, confidence and provenance on every hit, and a calibrated refusal when nothing clears the threshold.
pypi AGPL-3.0 ★ 7 -
MCP server for Manufacturer and Supplier Finder. Find manufacturers, wholesalers, and distributors for any product in 20 countries, each checked on its own website, with quoted evidence, domain, and a confidence score. Runs on Apify. Clay-ready output.
MIT -
MCP server for Company Headcount Estimator. Employee count band for any company domain from the LinkedIn company size in Google results, Wikidata, and the company site, with the source and a confidence score. Never opens linkedin.com. Runs on Apify. Clay-
npm MIT -
A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as an MCP server that needs no API keys in hosted mode.
npm MIT ★ 73 -
prworldsupdated this year
PR Worlds — the CLI and MCP server that gives your repo coherent, reproducible worlds your agent can open, replay, and inhabit. v0.2 ships the coherence resolver: agents see the plan's confidence, evidence, and explicit unknowns before the world is materi
npm MIT -
MCP server that lets Claude Code, Codex & AI agents drive a real Chrome browser with JEV (TypeSafe System One): ~100 ms typed decisions, calibrated confidence, human-in-the-loop questions, safety gates and a debug trace.
MIT ★ 7 -
MCP server for Company Headcount Estimator. Employee count band for any company domain from the LinkedIn company size in Google results, Wikidata, and the company site, with the source and a confidence score. Never opens linkedin.com. Runs on Apify. Clay-ready output.
MIT -
MCP server for Personal Email to Company Resolver. Find the likely employer behind a Gmail, Outlook, or other free mail signup, with a confidence and the public evidence, from Gravatar, signed GitHub commits, and LinkedIn results. Runs on Apify. Clay-read
npm MIT -
Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.
MIT ★ 6 -
MCP server for Person Social Footprint Mapper. Find a person's public GitHub, Bluesky, personal site, Substack, and X profiles from their name and company domain, with a match confidence per platform. No emails or phones. Runs on Apify. Clay-ready output.
npm MIT