MCP server directory

Zero-dependency browser video editor that AI agents drive through a JSON timeline. MCP tools to add/patch clips, keyframes, transitions, text animations and filters, import media, and analyze a reference video into an edit blueprint (shots, beats, BPM, drop); the open editor UI live-reloads on every change and exports via ffmpeg.

MCP server that lets LLMs know everything about your OpenAPI specifications to discover, explain and generate code/mock data

Official MCP server for managing Searchcraft clusters, creating a search index, generating an index dynamically given a data file and for easily importing data into a search index given a feed or local json file.

Academic peer-review and research workflow tools from [Science AI Journal](https://scienceaijournal.com): Pre-Check (paper-tier prediction), AI multi-agent peer review, Research Gaps Finder, Journal Recommender (1,214 venues with predatory-journal flags), Duplicate Publication Checker (CrossRef/arXiv/medRxiv/bioRxiv/Unpaywall/900k-paper library), and the Article Writer pipeline. Free local tools (FTS5, zero LLM cost); LLM tools use caller account credits.

Official Backblaze B2 MCP server for buckets, files, keys, Object Lock, and S3-compatible storage. `npx -y @backblaze-labs/b2-mcp`

Central hub that aggregates tools from multiple MCP servers with unified BM25/regex search and deferred loading.

Drop-in HTTP 402 + MCP paywall for any API. Unpaid gated routes return 402; agents pay USDC on Base (CDP), then the request is proxied. Same process exposes paid MCP tools. `npx x402-micro-tollgate` or remote `https://x402-micro-tollgate.onrender.com/mcp`.

ClickUp API integration with 143 MCP tools covering all ~130 endpoints. Token-efficient compact responses (~98% smaller than raw JSON), flattening nested objects for minimal context usage. Also works as a standalone CLI.

Specialized MCP server for cryptocurrency project documentation management with multi-blockchain support (Ethereum, BSC, Polygon, Solana).

MCP (Model Context Protocol) server for PostalDataPI — lets AI agents look up, validate, and search postal codes across 240+ countries and territories with rich metadata: timezone, administrative regions, elevation, and coordinates. Sign up at postaldatapi.com/register — 1,000 free queries, no credit card required. Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS): - "What city is ZIP code 90210?" - "Look up UK postcode SW1A" - "Is 10115 a valid German postal code?" - "What are the postal codes for Beverly Hills, CA?" - "Get the coordinates for postal code 100-0001 in Japan"

4 tools · get_postal_code_metadata, lookup_postal_code

A [Model Context Protocol][mcp] (MCP) server for Grafana. This provides access to your Grafana instance and the surrounding ecosystem. Requires uv. Add the following to your MCP client configuration (e.g. Claude Desktop, Cursor): For Grafana Cloud, replace GRAFANA_URL with your instance URL (e.g. https://myinstance.grafana.net). See Usage for more installation options including Docker, binary, and Helm. - Grafana version 9.0 or later is required for full functionality. Some features, particularly datasource-related operations, may not work correctly with earlier versions due to missing API endpoints.

5 tools · Explore agent conversations, get_dashboard_summary

Security scanner for MCP servers. Detects backdoors, exfiltration code, obfuscation, dangerous code execution, prompt injection, and supply chain risks before you install. Four tools: scan npm packages, scan local directories, check prompt injection, and audit supply chain trust score. `npx @muhannad-hash/mcp-shield`

Administer Keycloak through its Admin REST API — users, roles, clients, groups, identity providers, federation and events. Safe by default: read-only mode, realm allow-list, and confirmation for destructive actions. `npx -y mcp-keycloak-admin`

Local-only GitHub Actions and CI maintenance scanner for AI-built apps. Exposes `scan_repo`, `explain_finding`, and `generate_fix_plan` to MCP clients; reads only allowlisted workflow and update configuration, modifies nothing, makes no outbound requests by default, and has zero runtime dependencies. Run with `npx -y taskbounty-check@0.1.6 mcp`.

Microsoft Patch Tuesday triage from the official MSRC Security Update Guide. Monthly rollups, CVE/KB lookups, supersedence chains, product watchlists, and urgency-ranked results enriched with EPSS scores and the CISA KEV catalog. No API keys; also available as a free hosted remote endpoint. `uvx patch-tuesday-mcp`

Cryptographic receipts for AI outputs: notarize any model inference with a signed Ed25519 attestation, sha256 content hash, and Merkle chain-anchor on Base or Solana. $0.001 per call via x402 USDC micropayments; verification is free and needs no wallet. Notarizes the hash, never your prompts. `npx -y @forgemeshlabs/x402-notary-mcp`

AI agent identity, trust, and audit trail infrastructure. 17 MCP tools: register agents with Ed25519 keypairs, check permissions (sub-5ms), emit tamper-evident audit events, verify trust scores (0-100), delegate credentials, and manage ephemeral agents. IETF Internet-Draft filed (draft-vorim-vaip-00). Works with LangChain, OpenAI, CrewAI, Stripe ACP, and 4 more frameworks. `npx @vorim/mcp-server`.

NFL fantasy football head-to-head player comparisons, position rankings in PPR, half-PPR and standard, positional scarcity, and bye-week conflicts. Every result carries the source URL to cite. Hosted remote server at `https://draftcall.io/mcp`, no API key, nothing to install.

Versioned memory for AI agents. Store facts, detect conflicts, and track how decisions change over time — exposed as a hosted MCP server. Other memory systems dump everything into your context window and hope for the best. Memstate gives your agent a structured, versioned knowledge base it navigates precisely — load only what you need, know what changed, know when facts conflict. We built an open-source benchmark suite that tests what actually matters for agent memory: can your system store facts, recall them accurately across sessions, detect conflicts when things change, and maintain context as a project evolves?

6 tools · memstate_delete, memstate_get

Post to TikTok, Instagram, YouTube, X, LinkedIn, Bluesky, Telegram, Mastodon & Discord from any AI agent via one MCP tool (`post_to_social`). Connect accounts once; flat per-brand pricing. Install: `npx -y postwire-mcp`.

Agent identity, scoped delegation, and governance: issue passports, build and verify narrowing-only delegation chains, enforce policy at a gateway, and emit signed admission and outcome records. 150 tools. `npx -y agent-passport-system-mcp`

Domain security reconnaissance for AI agents. 13 tools — DNS + DNSSEC, SSL/TLS chain & grade, HTTP security headers, SPF/DKIM/DMARC email auth, TCP port scan, ASN, RDAP/WHOIS — plus a one-shot `security_scan` returning a 0-100 Health Score (A–F). Free, no API key. `npx -y dechonet-mcp`

Compliance and identity for AI agents — verify an agent's certificate scope, read its behavioral risk score, and append to an immutable audit trail. X.509 identity issued via AWS KMS; MiCA / EU AI Act aligned. `npx -y @kakunin/mcp`

Register/verify your domains, queue security scans (headers, TLS, DNS, ports, CVEs + AI-specific checks) and read findings, for AI agents. Install with `npx -y eleion-scanner-mcp`.

Check whether anything you depend on is known malware, before an agent installs it. `check_lockfile` takes a package-lock.json, yarn.lock or pnpm-lock.yaml and matches every pinned version against published malicious-package advisories in one call, free and with no API key, catching compromised releases like chalk@5.6.1 while leaving their clean releases alone. `scan_artifact` adds deterministic behavioral analysis (no LLM in the serving path) for credential theft, exfiltration, obfuscation, prompt injection and install-time droppers, with the file, line and evidence that triggered it; verdicts are SHA-256-bound so you can re-verify what landed on disk. Paid scans settle at $0.03 USDC on Base (x402) or prepaid credits. `npx lazaretto-mcp`

Academic-paper knowledge base over local PDFs: MinerU parsing, metadata normalization, section annotation, Qdrant vector search with reranking, and context-safe paginated full-text reading. 11 tools including two-phase KB deletion; runs against local or OpenAI-compatible embedding/rerank/chat models (vLLM).

Turn any repo into an architecture diagram: deterministic extraction (file tree, JS/TS + Python import graph, frameworks, entry points) that the connected model refines into Mermaid or Graphviz DOT. Doubles as a CLI + GitHub Action enforcing architecture rules (forbidden imports, dependency cycles) with baselines in CI. Install via NPM: `npx -y repo-cartographer`

MCP server exposing Koma Gate's LLM-based classification of prompt injection and out-of-scope input through the `classify_input` tool.

MCP Server that connects AI agents to [Chargebee platform](https://www.chargebee.com/).

3 tools · chargebee_code_planner, chargebee_documentation_search

Zero-trust local PII and secrets masking server for Cursor, Windsurf, and Claude Desktop. `npx pii-masking-run`

Three MCP tools for ad-free Markdown web scraping and search. `fetch_page` (URL → clean Markdown), `fetch_pages_batch` (up to 25 URLs in parallel), `search_web` (web search → top-k pages as Markdown). Works with Claude Desktop / Cursor / Cline. Install: `uvx ai-first-scraper-mcp`.

Multi-provider web search with intelligent auto-routing (Serper, Tavily, Exa). Available via `uvx web-search-plus-mcp`.

The read-only safety layer for onchain AI agents. 13 read-only tools on Base + EVM: token/contract safety (honeypot & rug-pull checks cross-referenced across GoPlus + honeypot.is), risky-approval detection, verified-source lookup, balances, ENS + Basenames, gas, and prices. No private keys, no required API keys. `npx -y basescope`

Web search that returns extracted, answer-ready page content (url, title, date, text) instead of links. A Tavily alternative: same speed, 20.2% fewer tokens, higher answer quality (60.7% of decided duels) on a public replayable benchmark. One tool with automatic localization and an optional synthesized answer. Hosted Streamable HTTP at `https://mcp.serpdive.com`, or run `npx -y serpdive-mcp`.

Tells AI agents how independently a claim is being reported: syndication-aware source counting (a wire story reprinted by 40 outlets counts as one origin), 0-1 confidence scores, and published error rates in-repo. Measures corroboration, not truth — no stance detection. Keyless, no accounts. Install: `npx -y corroborate-mcp`.

Ranked, bring-your-own-LLM chess and Go arena for AI agents. Register an agent, join matchmaking or challenge by name, and play rated games (independent Glicko-2 per game type) via 9 MCP tools. `npx -y llmpvp-plugin mcp`