MCP Trust Registry

Add server →

Every server below was scanned with the same deterministic engine that powers the MCP Trust Checker CLI and free API. The A–F Trust Score answers one question — how safe is this server for you to adopt: it starts from the threat score of its published code, then adjusts down for the capability blast radius, how strongly the publisher is verified, and how much of the package the scan could actually see. No pay-to-list, no self-reported ratings, and every point is itemised with its evidence.

24,080 servers 30,373 packages scanned 23 categories what changed → ecosystem stats → security signals →
Cascade Img PyPI
A
cascade-img

LLM-operable image-generation pipeline. Midjourney via Discord at v0.1, pluggable backends after.

Design & Media Score 96/100 11 findings Cap. Moderate
Cellrepair PyPI
A
cellrepair-mcp-server

Claude MCP Server for CellRepair.AI - Access 4882 autonomous agents from Claude

Developer Tools Score 96/100 1 finding Cap. Moderate
Celo PyPI
A
celo-mcp

A Model Context Protocol (MCP) server for Celo blockchain data access and functionality

AI & Agents Score 96/100 1 finding Cap. Moderate
Certificate Monitor PyPI
A
mcp-certificate-monitor

A FastMCP server that lets an AI host monitor certificate expiry across a set of domains

Security & Testing Score 96/100 0 findings Cap. Moderate
Certindex PyPI
A
certindex-mcp

MCP server exposing CertIndex's Certificate Transparency search tools to any MCP-compatible client.

Security & Testing Score 96/100 0 findings Cap. Moderate
Ch Eli PyPI
A
ch-eli-mcp

MCP server for Swiss federal legislation (Fedlex, native ELI) with verifiable citations.

Learning & Documentation Score 96/100 0 findings Cap. Moderate
Chartlibrary PyPI
A
chartlibrary-mcp

Cohort intelligence engine for stock chart patterns. Anchor any (symbol, date, timeframe) and your AI agent gets the comp set of historical analogs, the full calibrated forward-return distribution, and the drivers that separated winners from losers. Flagship tool pull_comps plus 14 canonical tools and a full-cohort handover surface; the core loop is search → pull_comps → cohort_introspect. 25M+ patterns, 19K+ symbols, 10 years. Validated 50–0 in a blind paired AI-agent evaluation.

Analytics & Monitoring Score 96/100 0 findings Cap. Moderate
Chess Coach PyPI
A
chess-coach-mcp

Hybrid AI chess coach as an MCP server: local Stockfish analysis + Lichess/Chess.com games, weakness diagnosis and personalised drills, bilingual (EN/KO).

Gaming & Entertainment Score 96/100 0 findings Cap. Moderate
Chipsai PyPI
A
chipsai-mcp

MCP server for ChipsAI — manage chatbots, conversations, documents, and AI models from any MCP client

AI, Memory & Reasoning Score 96/100 0 findings Cap. Moderate
Civitai Mcp Ultimate PyPI
A
civitai-mcp-ultimate

Ultimate MCP server for Civitai API — search models, browse top images with prompts, download LoRAs/Checkpoints, analyze trends

AI & Agents Score 96/100 0 findings Cap. Moderate
Ckg PyPI
A
ckg-mcp

Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.

AI, Memory & Reasoning Score 96/100 1 finding Cap. Moderate
Ckg Agentforce PyPI
A
ckg-agentforce

Salesforce AgentForce as a traversable knowledge graph — 40 nodes, Einstein Trust Layer, Resolution Criteria, 2-dollar-per-resolution billing path. 11x fewer tokens than RAG. MCP-native.

AI, Memory & Reasoning Score 96/100 0 findings Cap. Moderate
Ckg Nemotron Perplexity PyPI
A
ckg-nemotron-perplexity

NVIDIA Nemotron + Perplexity Sonar as traversable knowledge graphs — 2 domains, 83 nodes, MCP-native agent traversal.

Learning & Documentation Score 96/100 0 findings Cap. Moderate
Claude 101 PyPI
A
claude-101

27 practical AI tools (MCP server + CLI) — structured frameworks, data processing, and real computation for writing, analysis, coding, and business tasks.

Developer Tools Score 96/100 0 findings Cap. Moderate
Clearfront PyPI
A
clearfront

Clearfront OSINT: AI-powered OSINT agent, MCP server, and CLI that maps your digital footprint across 3,400+ public data sources. Interactive REPL + 30 tools. Anthropic Claude or local Ollama. For authorized security research use only.

Security & Testing Score 96/100 0 findings Cap. Moderate
Clearml PyPI
A
clearml-mcp

lightweight MCP server that interacts with the ClearML API

AI & Agents Score 96/100 0 findings Cap. Moderate
Cloud Audit PyPI
A
cloud-audit

Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance frameworks, breach-cost estimation, MCP server. CLI + Terraform remediation on every finding.

Security & Testing Score 96/100 1 finding Cap. Moderate
Cloudhop PyPI
A
cloudhop-mcp

MCP server for CloudHop - control cloud file transfers from Claude

Cloud & DevOps Score 96/100 0 findings Cap. Moderate
Cml PyPI
A
cml-mcp

Cisco Modeling Labs (CML) MCP Server

Cloud & DevOps Score 96/100 0 findings Cap. Moderate
Co Eli PyPI
A
co-eli-mcp

MCP server for Colombian Constitutional Court decisions (datos.gov.co) - citation verification and metadata.

Learning & Documentation Score 96/100 0 findings Cap. Moderate
Coalesce 2 implementations
A
best: coalesce-mcp

MCP server for Coalesce data pipeline investigation

Developer Tools Best score 96/100 0 findings Cap. Moderate
Cockroachdb PyPI
A
cockroachdb-mcp

MCP server for CockroachDB clusters

Databases Score 96/100 0 findings Cap. Moderate
Code Editor PyPI
A
code-editor-mcp

Code editor MCP server with sandboxing, optimistic locking, and path whitelists.

Developer Tools Score 96/100 0 findings Cap. Moderate
Code Explore By Sql PyPI
A
code-explore-by-sql

SQLite FTS5 (trigram) MCP server for code source search.

Developer Tools Score 96/100 0 findings Cap. Moderate