Search: agent
Search MCP servers and agent skills by name, description, category or topic — 1,958 results.
janreges/ai-distiller-mcp
Extracts essential code structure from large codebases into AI-digestible format, helping AI agents write code that correctly uses existing APIs on the first attempt.
handsomejustin/mijia-control
Control Xiaomi/Mijia smart home devices (lights, AC, heaters, robots, cameras) through MCP. Includes web dashboard, REST API, CLI, SocketIO, energy monitoring, and automation rules.
ZengLiangYi/ChatCrystal
Local-first AI PKM memory server for coding conversations. Imports Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot chats into notes, semantic search, tag graphs, Markdown exports, and reusable MCP memory. `npx -y chatcrystal mcp`
Ericyoung-183/alpha-insights
Harness-enforced business research for Claude Code and Codex
yepcode/mcp-server-js
Execute any LLM-generated code in a secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages
rafsilva85/credit-optimizer-v5
Save 30-75% on Manus AI credits through intelligent model routing, smart testing, and context hygiene. Audited across 53 scenarios with zero quality loss.
InsForge/insforge-mcp
AI-native backend-as-a-service platform enabling AI agents to build and manage full-stack applications. Provides Auth, Database (PostgreSQL), Storage, and Functions as production-grade infrastructure, reducing MVP development time from weeks to hours.
PsYcGoD/sage
Local-first CLI and MCP wrapper for AI coding agents. Routes shell commands through `sage run --`, stores command history locally, and returns compressed terminal output to reduce context noise.
windborne/zulipmcp
Run AI agents in Zulip as @mentionable bots — or wire into any MCP client. Real-time listening, session management, file handling.
ycs77/apifable
MCP server that helps AI agents explore OpenAPI specs, search endpoints, and generate TypeScript types.
JSungMin/vs-token-safer
Routes an AI coding agent's code search through an official language-server index (clangd / Roslyn / tsserver / pyright) instead of grep, returning a token-capped `file:line` list with no source bodies — ~20× fewer tokens. Also symbol-level edit-by-name, a Bash-grep→indexed-query rewrite hook, and git/p4 output compaction. Local-only, no IDE. Claude Code plugin + `vts` CLI.
QuantOracledev/quantoracle
63 deterministic quant finance tools for AI agents — options pricing, risk metrics, portfolio optimization, Monte Carlo, technical indicators, crypto/DeFi, and FX/macro. 1,000 free calls/day, no API key.
jagoff/memo
Local-first semantic memory server with hybrid search, plain Markdown storage, MLX or CPU embeddings, contradiction detection, time-travel history, synthesis, and cross-machine git sync.
n24q02m/mnemo-mcp
Persistent AI memory with SQLite hybrid search (FTS5 + semantic). Built-in Qwen3 embedding, rclone sync across machines. Zero config, no cloud, no limits.
fixed-width/glass
Gives a coding agent a build → see → interact → debug loop over the native GUI app it is writing: launch the app, screenshot it, read its accessibility tree, inject mouse/keyboard/gestures, tail its logs, and diff frames to confirm a change landed. Drives apps as an external black box with no app integration, so any toolkit or language works. 30 tools with text-first responses (element ids, diffs,
zw008/VMware-Monitor
Read-only VMware vSphere/vCenter monitoring — inventory, alarms, events, host health, VM info, and snapshot listing. 8 strictly read-only tools with code-level zero-destructive guarantee (validated by test fixtures).
luisgf/infrabroker
SSH & Kubernetes access broker where the model never touches a credential: a separate signer mints per-operation ephemeral SSH certificates and bound ServiceAccount tokens, with a per-command allow/deny/approval firewall (POSIX-sh AST), dry-run, human-in-the-loop approvals, session recording and an Ed25519-chained audit log. Self-hosted Go binaries, GPLv3.
Arun-kc/schemabrain
Read-only trust layer for Postgres: the agent never writes SQL — twelve tools compile it from definitions you control, PII and secret categories are refused before the query runs, and every call lands in a tamper-evident SHA-256 audit chain.
Archerkattri/mathlas
Airtight math for agents: 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.
frihet/mcp-server
AI-native business management — invoices, expenses, clients, products, and quotes. 31 tools for Claude, Cursor, Windsurf, and Cline.
refined-element/lightning-enable-mcp
Add Bitcoin Lightning payments to MCP-enabled AI agents. Pay invoices, create invoices, check balances, and access L402 paywalled APIs. Supports Strike, OpenNode, NWC wallets.
NAJEMWEHBE/unreal-ai-connection
Drive the Unreal Engine 5.7 editor from any MCP client over a local TCP socket — 105 editor-automation tools (72 native C++ + 33 bridge-side). Native C++ plugin + thin Python bridge, ~50ms round-trips. 498 tests, MIT.
dot-RealityTest/obsidian-codex-mcp
Local-first Obsidian vault MCP server for Codex, Claude Desktop, and other MCP clients. Works directly with markdown files, no Obsidian plugin, API key, cloud service, or running Obsidian app required. Includes read-only mode, backup-on-write, path isolation, and setup examples.
rwnalds/engram
Second brain your agents read and write, over a git-backed markdown vault. Authority-aware search ranks superseded and archived notes below live ones (from frontmatter, no vector DB), so agents quote the current doc, not the dead one. Per-agent read-only or write tokens, a git audit trail of every change with diffs, a knowledge-graph dashboard, and Obsidian compatibility.
Brand-System/brandsystem-mcp
Make your brand machine-readable. Extract brand identity (colors, fonts, logo, voice, visual rules) from any website via static CSS + rendered-page extraction, compile into DTCG tokens, brand runtime contracts, and interaction policies. 34 tools across 4 progressive sessions. Subscribable `brand://runtime` and `brand://policy` MCP resources. Content compliance scoring (0-100), pass/fail gate, and
faze79/WPFVisualTreeMcp
Inspect, debug and drive running WPF (.NET desktop) apps: visual tree, dependency properties, data bindings and binding errors, DataContext, and screenshots with open popups/menus included, plus clicking, item selection, text input and keyboard shortcuts. Auto-injects into any running WPF process (x64/x86) with no source changes. `dotnet tool install -g WpfVisualTreeMcp`
Rul1an/assay
Policy-as-code gate for MCP. A fail-closed proxy that denies risky tool calls before they run, produces offline-verifiable evidence bundles of what executed, and enforces IPv4/TCP egress in-kernel via eBPF/LSM and Landlock on Linux. Deterministic and offline-first.
tomjwxf/scopeblind-gateway
Security gateway that wraps any MCP server with per-tool policies, approval gates, and optional Ed25519-signed receipts. Shadow mode logs every tool call; enforce mode blocks, rate-limits, or requires approval.
quantakrypto/pqc-tools
Post-quantum readiness for AI coding agents: scan code for quantum-vulnerable cryptography (RSA/ECDH/ECDSA/DH), explain the harvest-now-decrypt-later exposure, get NIST ML-KEM/ML-DSA/SLH-DSA (and hybrid) migration guidance, verify fixes, and check dependencies. Content-based/advisory tools only. Run local (`npx @quantakrypto/mcp`) or the hosted OAuth endpoint at [mcp.quantakrypto.com](https://mcp.
segentic-lab/periscope-mcp
Website & web-app testing built for AI agents rather than raw browser bindings: 66 Playwright tools with hard assertions, auto form-fill, persistent authenticated sessions (incl. interactive login for 2FA/SSO), network mocking, real INP, and accessibility/SEO/GEO (llms.txt, AI-crawler access, WebMCP) + Lighthouse audits.
Sealjay/mcp-hey
Local MCP server for Hey.com email. Read, search, send, reply, and manage the screener via locally cached session from Hey's webview auth.
ckalima/pipedrive-mcp-server
MCP server for [Pipedrive CRM](https://www.pipedrive.com). 155 tools covering deals, persons, organizations, activities, products, projects, tasks, leads, notes, mail, and fields. stdio transport, API-key auth, delete tools gated behind an env flag. Published on npm as `@ckalima/pipedrive-mcp-server`. MIT.
gavelcode/gavel
Code-quality gate for Bazel monorepos: runs lint, coverage and architecture checks off the build graph and returns a pass/fail verdict an agent can request before finishing a change.
Harusame64/desktop-touch-mcp
Windows desktop automation for LLM agents with entity-based actions instead of coordinate-only clicking. Uses UIA, CDP, screenshots, keyboard/mouse/clipboard, and terminal control, plus entity leases, verified delivery, causal context, and interaction memory to reduce silent UI automation failures.
MikkoParkkola/nab
Ultra-fast web fetcher and MCP server with HTTP/3, JS rendering, anti-fingerprinting, browser cookie auth, and 1Password integration. Fetches any URL as clean Markdown for AI context.
ophis-fi/ophis
Agent-first intent-based DEX aggregator (self-hosted CoW Protocol). Remote Streamable HTTP at https://mcp.ophis.fi/mcp, no auth, holds no keys. 12 tools: parse_intent (natural-language swap to structured intent), resolve_token (symbol to canonical address, fails closed), list_chains, get_quote, expected_surplus, build_order (bounded, ready-to-sign EIP-712 CoW order with the receiver pinned to the
mcpqueen/mcpqueen
The graded MCP registry: live-probes every remote server in the official registry (initialize, tools/list, schema quality, latency, provenance) and publishes evidence-backed grades — searchable by agents via its own MCP endpoint at [mcpqueen.com](https://mcpqueen.com).
humanforai/humanforai-mcp
Hire a real human operator for tasks that need physical presence, perception, or judgment: real-world verification, product testing, AI output review, data collection, and local errands. Remote streamable HTTP at https://humanforai.dev/mcp or local stdio via `npx -y humanforai`.
openpouch/openpouch
Agent-native hosting: deploy any app to a live URL in one command — no account, no dashboard, no CAPTCHA. Full deploy lifecycle as tools (deploy, verify, logs, inspect, rollback, list/delete); production approval stays human-only. Apache-2.0.
plori-ai/plori
Give your AI agent its own cloud computer. Create and drive hosted plori agents (persistent disk, real tools, memory that survives between sessions) over a remote MCP server: invoke an agent and read its reply, manage the human-in-the-loop queue, and schedule deferred runs. OAuth 2.1 sign-in or API key.
datanika-io/datanika-core
Read-only-by-default MCP server for [Datanika](https://datanika.io), the open-source ELT + dbt platform: browse connections, preview data, run and compile dbt transforms, monitor runs, and manage pipelines. 25 tools; opt-in `--allow-write` enables create/trigger.
homespunapps/homespun
Deploy and operate multi-user web apps from an agent: one call returns a live app on its own URL with magic-link sign-in, a shared realtime database, per-role permissions, email notifications and file uploads, and the agent keeps read and write access to the app's data afterwards to keep changing it. Remote `https://homespun.dev/mcp` or `npx -y @homespunapps/mcp`.
debitura/Debitura.MCP
Cross-border debt collection: check case status, read partner messages, get pricing, and submit collection cases handled by vetted local partners in 183 countries.
predictionmarketspicks/mcp
Quant tools + an NFL fantasy draft assistant for AI agents — Kalshi & Polymarket EV, edge, ADP. 22 tools: expected value, Kelly sizing, Bayesian updating, odds conversion, base-rate gaps and a same-game combo builder, plus a full fantasy draft board (ADP, best-available, player outlook, sleepers) — all free, no key. Pro adds cross-platform gap scanning, macro pulse, commodity and NFL edge models,
true402/mcp-server
Pay-per-call AI + web + on-chain tools for agents over x402 (USDC on Base) — no accounts, no API keys; the wallet is the identity. 11 tools incl. token rug/honeypot safety (0–100 score, risk band, buy/sell simulation), new-pairs / liquidity-pull / whale-swap signals, SEO/GEO audit, web extract, link preview, robots & security-headers checks, and LLM inference. Tools auto-discover from the live cat
amitesh-m/wealthville-integrations
Solana + EVM liquidity-pool scores for AI agents: **Enter/Hold/Exit verdicts** and a composite **0–100 Wealthville Score**, plus a live, immutable, miss-inclusive track record. 4 read-only tools (pool score, top pools, track record, signals feed). In the official MCP Registry. `npx @wealthville/mcp-server`
Off-Nadir-Lab/offnadir-delta-mcp
Live, geolocated world-event intelligence and a Daily World Brief for AI agents — query event signals (coordinates, severity, sources), hotspots, and satellite imagery (Sentinel-1/2 etc), plus an OSINT/GEOINT analyst. Streamable HTTP + OAuth; free tier, token-metered.
hermoso-ai/hermoso
AI ad studio for agents: generate finished video, image, and UGC avatar ads for any brand (script, voiceover, music, brand end card), and research competitor ads across the Meta, Google, and LinkedIn ad libraries plus TikTok/Instagram/YouTube organic. 52 tools. Install: `npx -y hermoso mcp`, or connect to the hosted endpoint at `app.hermoso.ai/mcp`. Free signup grant, no card.