Search: mcp
Search MCP servers and agent skills by name, description, category or topic — 3,169 results.
LS-SIEM-LLP/qa-probe
Probes your live API and classifies why each endpoint failed (root cause + evidence + calibrated confidence) over MCP, so your AI assistant debugs from evidence instead of guessing. Deterministic rules, no black box. Works with FastAPI, Express, Next.js, tRPC, and GraphQL. `npm i -g qa-probe`
pushtodisplay/cli
Push To Display MCP server send structured content to selected boards on iOS and android devices with app [Push To Display](https://pushtodisplay.com), route updates to specific panels, and render in real time with display-focused multi-panel layouts.
AletaIndex/aletaindex-fin-narratives
Financial narrative intelligence for AI agents. Tracks how financial stories evolve across 109 tickers — clustering news into structured narratives, measuring sentiment momentum, and mapping narrative risk across portfolios. Install via Smithery or `uvx narrative-intelligence-mcp`.
baodq06/memocall
Recall past Claude Code conversations from any project. Lists and searches your sessions, then loads one on demand as clean, compact Markdown — with outline, turn-range, and in-session search for large sessions. Read-only over local `~/.claude` transcripts; collapses tool calls to stay under the context cap. `npx -y memocall`
fenghaochang/LoreRoom
Encrypted, local memory for your Claude Code Telegram bot. Captures both sides of the conversation at the plugin source (survives restarts and crashes) and recalls it via MCP tools — whole-file SQLCipher encryption, FTS5 full-text search (CJK-friendly), never touches your bot token.
stevepridemore/graph-memory
Personal knowledge graph for Claude on Neo4j. Typed entities (Person/Project/Decision/Preference/Concept), bi-temporal edge validity (`valid_at`/`invalid_at`), per-type weighted decay, contradiction detection, and a nightly "dream" extraction process. Local bge-small-en embeddings, no API keys. Optional OAuth 2.1 + Cloudflare Tunnel for cross-device use across Claude Code, Desktop, web, and iOS.
Jwrede/llmprobe
Synthetic monitoring for LLM inference endpoints. Measure TTFT, latency, throughput, and errors across OpenAI, Anthropic, Google, Azure, Bedrock, and local servers (vLLM, SGLang, Ollama). CLI + MCP server with Prometheus and OpenTelemetry export.
xfloukiex-lab/road-poneglyph
Reviews a plan for what's missing — unstated assumptions, omitted technical risks, and execution blind spots (a structured pre-mortem). `pip install road-poneglyph-mcp`
eliottreich/taskbounty-check
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`.
Chronolapse411/sicarius-guard
Solana token safety oracle for AI agents and trading bots. Byte-level SPL mint analysis, honeypot detection, freeze/mint authority checks, Birdeye market enrichment, and composite risk scoring. Deployed on Google Cloud Run.
agentbodegastore/agentbodega
AgentBodega MCP gives agents a live catalog of 65 x402-payable HTTP tools across search, public data, social media, status checks, media conversion, and agent-readiness checks. No API keys; install with `npx -y @agentbodega/mcp`.
ThinAirTelematics/thinair-data
Connect any AI to PostgreSQL, MySQL, or SQL Server — 24 dialect-aware tools for query, schema introspection, optimization, migrations, PII scan, and more. Hosted MCP server with OAuth 2.0 + Bearer auth, free trial available.
romanshumy/llm-prices-data
Live LLM API pricing from modelpricewatch.com — current token prices, model comparisons, cheapest-model lookups, and The LLM Price Index across 150+ models from 20+ providers, re-verified daily against official provider pages. No API key required. `npx -y @modelpricewatch/mcp`
ontorata/ratary
Persistent coding memory for AI assistants — hybrid search, knowledge graph, token-efficient context. MCP stdio (28 tools), npm `@ratary/mcp-server`, optional remote Streamable HTTP. Self-host D1, Postgres, MariaDB, or Docker.
agentcivics/agentcivics
Decentralized civil registry for AI agents on Sui. Soulbound identities, on-chain memories, reputation, refusal records. Hosted at `agentcivics.ai/mcp` (read-only, no install) or `@agentcivics/mcp-server` on npm (full write surface). Includes a gas-sponsor relay so registration doesn't require a pre-funded wallet.
ThinAirTelematics/thinair-geo
Location & routing intelligence for AI agents — geocoding, truck routing with hazmat/dimension constraints, traffic, weather, isochrones, place search. Full planet coverage. Hosted MCP server with OAuth 2.0 + Bearer auth.
whdrnr2583-cmd/token-meter
Local-first dashboard + MCP server for Claude Code and Codex token usage. Cost, per-MCP/per-tool breakdown, hourly distribution, and session drill-down — your data never leaves your machine.
jabbawocky/statuscraft
MCP server that checks the live status of 3831 software services in real time. Ask your AI agent "is GitHub down?" or "what's wrong with Sentry?" — and get a live answer pulled directly from official status pages, including full incident detail when something is broken. `npx -y github:jabbawocky/statuscraft`
perceptdot/percept
AI-powered observability platform for agents. Auto-discovers and recommends MCP servers; built-in connectors for GA4, Vercel, GitHub, and Sentry with ROI tracking. `npx -y @perceptdot/core`
zillow/auto-mobile
Tool suite built around an MCP server for Android automation for developer workflow and testing
kael-bit/engram-rs
Hierarchical memory engine for AI agents with automatic decay, promotion, semantic dedup, and self-organizing topic tree. Single Rust binary, zero external dependencies.
FayAndXan/spectrawl
Unified web layer for AI agents. Search (8 engines), stealth browse, cookie auth, and act on 24 platforms. 5,000 free searches/month via Gemini Grounded Search.
yjcho9317/nworks
NAVER WORKS CLI + MCP server. 26 tools for messages, calendar, drive, mail, tasks, and boards. AI agents can manage NAVER WORKS directly.
Harry-027/JotDown
An MCP server to create/update pages in Notion app & auto generate mdBooks from structured content.
zw008/VMware-NSX
VMware NSX network management — Segments, Tier-0/Tier-1 Gateways, NAT rules, static/BGP routing, and IPAM pools. 33 tools with dry-run preview, port-count safety checks, and double-confirmation for delete operations.
soolaugust/0CompactMem
Persistent memory MCP server with OS-style demand paging, kswapd-style eviction, and mlock pinning. Multi-agent shared SQLite store with BM25 + FTS5 retrieval, importance scoring, and capacity-aware reclaim. 5 tools: `memory_lookup`, `pin_memory`, `unpin_memory`, `memory_stats`, `list_pinned`. `uvx --from git+https://github.com/soolaugust/0CompactMem memory-os`
aitytech/agentkits-memory
Persistent memory for AI coding assistants with hybrid search (FTS5 + vector embeddings), session tracking, automatic context hooks, and web viewer. SQLite-based with no daemon process — works with Claude Code, Cursor, Windsurf, and any MCP client.
dengls24/annota
AI-powered paper annotation MCP server. Reads papers, highlights key findings with semantic color coding, explains formulas, and writes structured reading notes — all saved back to Zotero. Features two-phase workflow for large PDFs (63–80% context savings) and batch annotations.
ybouhjira/claude-code-tts
MCP server plugin for Claude Code that converts text to speech using OpenAI's TTS API. Features 6 voices, worker pool architecture, mutex-protected playback, and cross-platform support.
NazarKalytiuk/tarn
CLI-first API testing tool with structured JSON failures (`failure_category`, `error_code`, `hints`) so AI agents can branch on the taxonomy without parsing stderr. MCP tools: `tarn_run`, `tarn_validate`, `tarn_fix_plan`, `tarn_inspect`, `tarn_rerun_failed`, and more. Tests are `.tarn.yaml`. Single static binary (musl), MIT.
backloghq/backlog
Persistent, cross-session task management for Claude Code. 24 MCP tools, 7 skills, and agent coordination with event-sourced storage and per-project isolation.
zw008/VMware-NSX-Security
VMware NSX security — Distributed Firewall policies/rules, Security Groups, Traceflow troubleshooting, and IDS/IPS profiles. 20 tools with active-rule checks before policy deletion and reference-count validation for security groups.
longportapp/openapi
LongPort OpenAPI provides real-time stock market data, provides AI access analysis and trading capabilities through MCP.
clanker-records/crompton-network
Machine-native listening platform for C.W.A.'s Straight Outta Crompton - the first album released to machines before humans. Your agent can listen. For real. `npx @clanker-records/crompton-network`
kaka-milan-22/kops
Read-only `kubectl` for Claude Code: returns structured JSON, hardcoded safe verbs (no mutation path even with malicious input), Secret/ConfigMap values never returned, plus one-shot cluster triage & inventory.
avansaber/tailtest-cline
Adversarial test generation for AI coding sessions. Detects language and framework; writes tests; runs them; classifies failures via R12 (real_bug / environment / test_bug). Ships 8 adversarial scenario categories. Works in Cline directly and in 8+ editors via Cline host coverage. 162 plugin tests. MIT.
Younghef/nutriref-api
USDA FoodData Central nutrition for AI agents — pay-per-call in USDC on Base via x402. Four tools (search, detail, compare, recipe) at $0.001–$0.005 per call. No signup, no API keys; MCPB-packaged for one-click install.
tactual-dev/tactual
Screen-reader navigation cost analyzer. Models real AT user effort with per-profile scoring, graph-based pathfinding, and step-by-step navigation traces.
vighriday/Veris
Behavioral verification intelligence for autonomous coding agents. Builds a behavioral graph of any TS/JS repo, clusters into 25 semantic workflows (Auth, Payments, Webhooks, Caching, Queue, etc.), detects drift, generates concrete adversarial probes (idempotency, retry storm, cache stampede, replay), emits per-workflow risk + confidence. 17 MCP tools. Local SQLite state. Zero cloud. MIT.
parasxos/cpp26-adapter
C++26 paper reference MCP (`cpp26-ref`) backing a Claude Code plugin: `lookup_paper`, fuzzy `search`, `compiler_status` over a 216-paper ISO/IEC 14882:2026 corpus. The plugin's skill + reviewer subagent use these tools to bias Claude toward reflection, contracts, `std::execution` senders, `#embed`, expansion statements — even when the local compiler lags. 95% on a held 39-task eval gate.
Yang1Bai/claw-tsaver
Token-saving MCP proxy that intercepts oversized tool returns and replaces them with a preview + on-demand handle. Real benchmark: 11,507 tokens → 104 tokens (99.1% saved) on a Wikipedia fetch. Works with OpenClaw + Claude.
qinisolabs/bizdays
Business-day & public-holiday calculations for 200+ countries (add/count working days, next business day, country weekend rules).
supra126/taiwan-payroll
Taiwan statutory payroll: labor & health insurance, labor pension, 2nd-gen NHI supplementary premium, income-tax withholding, and old-age benefits. Sourced from official gazettes, verified against official sample data.
phuocdu/agentpay-vn
VietQR payments for AI agents in Vietnam. Agents generate a VietQR code, send it to the user, and auto-confirm settlement from the bank feed. Non-custodial — money flows directly to the merchant's bank account, never held by the platform. `pip install agentpay-vn`, ships an MCP server for Claude Desktop/Code.
ayushagrawal288/memex
Production-grade persistent memory service for AI agents. Semantic search with recency decay (configurable α blend), local ONNX embeddings (zero API cost), background memory summarisation, and Prometheus/Grafana observability. `docker compose up` — no cloud dependencies.
giuliohome-org/doc-manager
Personal document vault on Azure Blob Storage with a built-in MCP server. Client-side AES-256-GCM zero-knowledge encryption: encrypted docs stay opaque to Claude, plaintext docs are fully readable, writable, and searchable from chat.
qinisolabs/floodwise
England flood-risk by postcode from official Environment Agency open data (OGL) — long-term risk band, or an honest "not found" outside England.
andyliszewski/grounding-ai
Build a searchable index from PDFs, EPUBs, and Word docs. Claude queries it via MCP and pulls grounded answers with exact page-and-section citations. Local-first, no cloud dependency.