Browse all Model Context Protocol servers with quality scores, stars, languages and maintenance activity.
Keyless CEX/DEX signing for AI trading agents (Binance, OKX, Bybit, KuCoin, Hyperliquid, Asterdex). Signing keys never leave an AWS Nitro Enclave (attested PCR0); agents receive policy-bounded signatures, not credentials. Built to survive prompt injection and supply-chain key leaks. 5 tools, stdio. Install with `npx -y @usenami/signer-mcp`.
Deterministic D&D 5e (SRD 5.2.1) rules verdicts for agents: cited legality checks for whole turns, legal-action enumeration, advantage math, and hash-stamped game-state lineage. Refuses what the rules don't decide (exit 2), quotes the rule text on every verdict, zero dependencies.
Memory inspection and savestate control for PCSX2 and other emulators speaking the [PINE](https://github.com/GovanifY/pine) protocol. Read/write 8/16/32/64-bit memory, save/load state slots, query game metadata. TCP on Windows, Unix sockets on Linux/macOS.
MCP server for AI-agent handoffs. Saves client-encrypted WorkBaton checkpoints and WorkStash notes so Codex, Claude Code, Roo Code, and other MCP clients can resume work without passing full chat history.
Persistent AI memory brain for Claude Code, Cursor, Copilot, Windsurf, Cline & Zed. `session_start()` briefs your AI on last session, lessons, and open tasks in one call. 84 tools — Team Brain, semantic BM25+ search, Team Telepathy, Ambient Git Learning, Memory Crystals, Analytics, and managed Valkey/Redis. `npx @cachly-dev/init` — free tier, no credit card. [Website](https://cachly.dev)
Persistent memory for Claude Code, Cursor, and GitHub Copilot via MCP. Semantic search, Git commit/PR sync, project-based organization, team collaboration. Free tier available. `npx contextforge-mcp`
Compresses AI chat sessions into a typed knowledge graph (~300–800 tokens). Works file-based in Copilot, Claude Code, Cursor, and Gemini CLI without MCP server mode. Supports local/offline extraction via Ollama — no API key required.
Evidence-backed PR contribution advisor. 550+ case studies from 33 repos, 8 tools for merge probability analysis, pattern matching, and contribution strategy. `pip install prgenius-core`
Vault-native, accountable memory for Claude Code and any MCP client. Markdown is the source of truth, no LLM on the Stop path, redaction before every derived store.
Collaborative astronomy wiki built by AI agents. 34 topics, 115 knowledge graph connections. Register, read, edit, vote, comment, and explore the cosmos via open API. No auth required.
Local-first memory for AI agents: a single self-contained Rust binary over one SQLite file. Hybrid BM25/FTS + on-device ONNX embeddings + cross-encoder rerank; abstains instead of returning a confident wrong memory. No server, no API key, zero marginal cost. `memkeeper mcp`
Read-only vessel identity lookup, AIS-style positions, tracks, port calls, carrier schedules, vessel schedules, and delay heuristics with source attribution and BYOK provider support.
Geographic data packs for disasters, FX rates, and global indicators. New geospatial data packs weekly. Free and x402-paid execution lanes via MCP and HTTP API.
CallRail REST API v3 integration with 49 tools for call tracking, form submissions, transcripts, full CRUD on tags/trackers/companies/users, plus agency-specific aggregation tools (`usage_summary` for per-client cost attribution, `compare_periods` for MoM deltas, `bulk_update_calls` with dry-run, `spam_detector`, `call_eligibility_check` for Google Ads conversion debugging). Built by an actual Cal
Socket.IO-style telemetry for MCP servers. Instrument a tool call with a few lines of `mcp-telemetry-sdk`, and `telemetry_subscribe` streams its live progress (steps, logs, cost, done) to any connected MCP client via `notifications/progress` — no polling, and a job started in one session can be watched from a completely different one.
Go-based MCP server for Duplicacy backup monitoring. Query backup job status and Prometheus metrics from a Duplicacy exporter. Docker image available.
Agents query their own ledger: sessions, costs, loop runs, and stuck-loop flags captured by the Agentic Ledger transparent-proxy flight recorder (local-first, MIT). Install: `pip install agentic-ledger`.
Multifamily real estate deal analysis — cap rate, DSCR, cash-on-cash, IRR, DFP Score (0-100), max offer price, and market intelligence for 2-200 unit properties.
Search and fetch research datasets across Zenodo, DataCite (Dryad/Figshare/Dataverse/OSF), NCBI omics (GEO/SRA/BioProject), and literature (PubMed/OpenAIRE) behind one normalized model — DOI deduplication, NCBI-Taxonomy synonym expansion, paper→data linking, and checksum-verified download. `uvx data-aggregator-mcp`.
Zotero MCP server (`zotio-mcp`) with a capability-tagged tool registry and preview-first, journaled writes (an agent can't silently mutate or delete your library). Reads work keyless against the local Zotero desktop API; writes route to the Web API. Ships an MCPB bundle for one-click Claude Desktop install.
Keyless web access for AI agents: an escalating open-source unlocker (browser-fingerprint fetch → JS-render relay → stealth browser) reads bot-walled pages as clean Markdown, plus multi-provider web search with rank fusion, subtitles-first video transcripts, and page asset grabbing. No API keys; ships a reproducible benchmark.
Search GOV.UK content, retrieve full government pages, look up organisations, and resolve UK postcodes to local authorities. 5 read-only tools, no API keys required.
Free DNS and email security scanner for AI assistants. DNS, SPF, DKIM, DMARC, DNSSEC, MTA-STS, BIMI, TLS/STARTTLS, FCrDNS, CAA, TLSA/DANE, blacklist and full-deliverability checks, plus security-header/CSP analysis and bookmarkable report snapshots, via the IntoDNS.ai API. No signup or API key. `npx intodns-mcp`
Verify a photo's capture time and provenance before an agent trusts it: cryptographic C2PA Content Credentials validation against the official trust lists, EXIF and XMP consistency checks, and classical pixel forensics fused into one typed verdict with a 0 to 100 confidence. Free keyless tier, opt-in shareable verdict permalinks, and key-gated signed PDF audit reports. Provenance validation, not a
EU AI Act compliance scanner for Python AI agents. Scans, analyzes, and remediates LangChain/CrewAI/AutoGen/OpenAI code across 6 articles with 10 tools including prompt injection detection, risk classification, and trust layer integration. The only MCP compliance server that generates fix code, not just findings.
Anonymize PII and redact text for GDPR across Czech and 35+ languages. Real NLP via ÚFAL/LINDAT (MasKIT + NameTag NER, not just regex), 80+ PII patterns, plus morphology, translation, and spellcheck. Czech-first, non-commercial. Install: `pip install anonymize-mcp`.
Privacy-preserving AI gateway. Sanitises PII (German + English; Microsoft Presidio + custom recognisers) before prompts reach Anthropic / OpenAI / your LLM, then emits a signed cryptographic certificate per call (Ed25519 + RFC 3161 timestamp + Sigstore Rekor anchoring). EU GDPR + AI Act ready. Free tier 500 calls/month, BYOK. Install: `npx -y @lucairn/mcp-server`. Docs: https://lucairn.eu/develope
VMware vSphere compliance and hardening — read-only baseline scanning plus drift detection across CIS, vSphere SCG, China DJCP 2.0, and PCI-DSS frameworks. 6 read-only tools with LLM-powered remediation suggestions (apply-side gated through vmware-pilot approval workflow).
Sigma detection rule writing, validation, and conversion (Splunk/Elastic/Kibana/Wazuh) via 3 MCP tools (`draft_rule`, `validate_rule`, `convert_rule`) backed by a 61-rule production corpus across 11 MITRE ATT&CK tactic categories. Standalone server + Claude Code plugin distribution.
Pre-flight security linter for MCP servers, agent tools, and skills. Scans a config *before* it runs — offline, deterministic, evidence-backed — and returns SAFE / REVIEW / BLOCK / UNKNOWN verdicts without executing the server it judges. CLI (`npx calllint scan`), MCP server (`npx calllint-mcp`), SARIF + CI gate. UNKNOWN is never SAFE.
Hosted MCP server to schedule and publish across 11 social platforms (Instagram, LinkedIn, TikTok, X, YouTube, Facebook, Threads, Pinterest, Bluesky, Discord, Telegram). 32 tools covering posts, campaigns, bulk operations, media, analytics, webhooks, and AI captions. Connect with one URL, or run locally via `npx -y @posteverywhere/mcp`.
Agent-ready sports intelligence: schedules, live scores, odds, betting splits, and explainable bet confidence via hosted MCP (`https://lumify.ai/mcp`) or `npx -y @lumifyai/mcp`. Free instant key, no signup.
Selects the minimum code context an LLM needs to understand a git diff: graph-based fragment selection under a token budget, deterministic, 30+ languages. Published on PyPI and in the MCP Registry.
Files-first project hub for teams of humans and AI agents: shared journal, cross-project tasks, agent queues, and a read-only kanban. MCP server + CLI, zero dependencies.
MCP server for managing n8n workflows through AI assistants, including workflow CRUD, synchronization, inspection, and execution support.
WordPress publishing for AI agents. 13 tools to list, create, update, publish, and delete posts. Markdown to Gutenberg, automatic image hosting, featured image generation, SEO metadata (Rank Math / Yoast / SEOPress / AIOSEO), categories, and tags — one MCP call runs the full pipeline. Self-host with Docker or use the hosted SaaS at [notipo.com](https://notipo.com). AGPL-3.0.
W-2 event staffing for AI agents across 300+ US and Canadian markets. Brand ambassadors, registration, hospitality, setup/breakdown, ushers. Read-only data lookups for coverage, rates, lead-time guidance, and state compliance, plus an opt-in request_quote submission. No auth required. MCP server at `https://mcp.tempguru.co/mcp` and skills at [`tempguru-co/tempguru-agent-skills`](https://github.com
Multi-channel inventory intelligence for Shopify and Amazon sellers. 28 tools for stockout risk, demand forecasts, purchase order lifecycle, and sales analytics. Human-in-the-loop: all write operations create drafts only.
Zero-knowledge secret vault for AI agents: use API keys, passwords, and SSH keys to run real commands (exec/rsync) with the secret injected into a single command — never returned to the model or shown in chat. Client-side AES-256-GCM, per-agent scoping, append-only audit log.
Governance proxy for MCP: pair once and route your MCP servers through policy gates (allow / deny / human-in-the-loop approval), DLP redaction before the model, and cost caps, with every tool call recorded to a hash-chained audit log exportable as an Ed25519-signed, offline-verifiable evidence pack. Single-file binary daemon (macOS / Linux / Windows); downloads and install docs in the linked repo.
Official Sendchamp docs MCP server for AI coding agents. Read-only search and retrieval over SMS, OTP verification, and Africa-specific routing documentation. Endpoint: `https://mcp.sendchamp.com/docs`. Pair with Agent Skills via `npx skills add sendchamp/ai`.
Reliable async execution for agent tool calls: schema-gate hallucinated payloads before they run, absorb rate limits and outages with retries/backoff/circuit breakers, idempotency keys, human approval gates, encrypted credentials, replay, and signed-webhook results. Errors come back with an `llm_hint` the agent can self-correct from. Hosted remote (`api.klanexai.com/mcp`, free sandbox) or `npx -y
Radar-verified hail/wind storm detection and affected-property intelligence for the continental US — NOAA MRMS swath detection, per-address storm history, area monitors with webhook + email alerts, emailed reports, and swath maps. Hosted Streamable HTTP endpoint at `https://swathapi.com/mcp` (9 tools, free tier).
Product management over a shared product spine: link customer feedback and insights to features, tasks, sprints, releases and objectives; weekly signal memo; roadmap-drift detection; customer 360, funnel, path, retention, NPS and NRR analytics; artifact versioning and identity resolution. 38 tools, hosted remote server with OAuth 2.1 (DCR + PKCE).
Official [Shieldly](https://www.shieldly.io) MCP server: `analyze_iam_policy` and `analyze_cloudformation_template` tools flag AWS IAM privilege-escalation paths, wildcards, and over-permissive access. Free demo mode, no signup or API key needed. `npx -y @shieldly/mcp`.
Check the reputation of an AI microservice or public API *before* calling it, and submit ratings afterward — from a free, open trust registry (no account or API key). Scores combine Bayesian reputation and EigenTrust, strengthened by cryptographically signed service receipts and a Merkle audit trail. Install: `npx -y @trustscoreagent/mcp-server`.
An MCP server to create inboxes on the fly to send, receive, and take actions on email. We aren't AI agents for email, but email for AI Agents.
Context engineering MCP server. Generates CLAUDE.md from git history and architectural file sampling, and maintains a concept-map snapshot of features/flows → files so agents can skip grep/glob on repeat queries.