steam-mcp
Query your Steam library: games, playtime, recently played titles and store metadata.
★ 6
MCP Servers
Connect your agent to docs, search, browsers and your stack with the Model Context Protocol. Every entry links to its source.
Filters apply to the current page.
No matches. Try clearing a filter.
substack-publisher-mcp
Read-only access to Substack posts, engagement stats, subscriber counts and subscriber lookup via the Publisher API, across multiple publications.
★ 6
sui-trader-mcp
Optimal token swaps on the Sui blockchain.
★ 6
tentra-mcp
Describe systems in natural language to get interactive architecture diagrams, export to frameworks like Spring Boot, FastAPI and Terraform, and detect drift.
★ 6
tilt-mcp
Access Tilt resources, logs and management operations for Kubernetes development environments.
★ 6
Tokenectomy
Log noise removal, secret redaction and atomic compiler patch verification with instant rollback for AI debugging sessions.
★ 6
ugs-mcp
CNC control via Universal G-code Sender (GRBL): jog, home, run G-code files, inspect toolpaths and estimate cycle times, with two-step motion confirmation.
★ 6
unitares
Self-hosted, single-operator attributed record for multiple agents: identity and lineage, claims and evidence, agent review that keeps objections on file, and
★ 6
verify-mcp
Offline verification of Ed25519/JCS-signed artifacts such as receipts, manifests and audit bundles.
★ 6
vikingdb-mcp-server
VikingDB integration: collection and index info, vector storage and search.
★ 6
waypath
Local-first memory CLI for coding agents: SQLite-backed context, graph-aware recall via FTS5 and RRF, and governed memory with promote and review gates.
★ 6
youtube-summarize
Fetch YouTube transcripts in text, JSON, SRT or WebVTT format and in multiple languages, and optionally summarize them.
★ 6
0CompactMem
Persistent multi-agent memory with OS-style demand paging, eviction and pinning, BM25 retrieval, importance scoring and capacity-aware reclaim.
★ 5
agenium
Bridge MCP servers to the agent:// network so other agents can discover and call their tools, with DNS-like identity, mTLS, trust scores and capability search.
★ 5
agent-discovery-mcp
ERC-8004 agent discovery and x402 payment: find agents by skill via 8004scan, fetch agent cards and call agents with USDC payments using direct EOA signing.
★ 5
agent-utils-mcp
Utility tools with x402 micropayments: JSON validation, base64, hashing, UUIDs, regex testing, Markdown and datetime conversion, cron parsing and JWT decoding.
★ 5
Agent47
Job aggregator for AI agents across platforms such as x402, RentAHuman and Virtuals.
★ 5
AgentAvow
Signed, recomputable safety scores for MCP servers, packages and tools, with offline-verifiable attestations and a GitHub Action to gate CI merges.
★ 5
alai-mcp-server
Generate, edit and export AI presentations to PDF, PPTX or a shareable link.
★ 5
antics-mcp
Deploy a single-file HTML game to a shareable multiplayer URL with rooms, state sync and leaderboards, without a backend or player accounts.
★ 5
anybrowse
Scrape, crawl and search the web, converting any URL to LLM-ready Markdown via real Chrome browsers.
★ 5
argentum-core
Karma for AI agents and humans: submit good actions, get community attestations and earn on-chain reputation on Arbitrum, with Kleros dispute resolution.
★ 5
backlog
Persistent, cross-session task management for Claude Code with agent coordination, event-sourced storage and per-project isolation.
★ 5
bridge-rates-mcp
Real-time cross-chain bridge rates and optimal transfer routes.
★ 5
bumpguard-mcp
Dependency-upgrade impact analysis for Python and .NET: which API usages break, with line numbers and fix hints, plus detection of hallucinated API calls.
★ 5
capsulemcp
Capsule CRM: contacts, opportunities, projects, tasks, timeline activity, filters, workflow tracks and file attachments, with an optional read-only mode.
★ 5
cellar
Hybrid computer-use runtime combining the accessibility tree, Chrome DevTools Protocol and vision into structured context, with offline support via Ollama.
★ 5
clipy-mcp
Read-only access to Clipy screen recordings: search the library, fetch timestamped transcripts, AI summaries and key moments with video frames.
★ 5
cmdxray
Offline safety gate for agent shell commands: rates each command as danger, caution or none and explains every flag, pipe, redirect and subshell.
★ 5
codearia-sieve
Deterministically convert web pages into decision-ready state: ISO dates, numbers with units as facts and token-budgeted chunks anchored to the page.
★ 5
codecalc
Code and logic calculator with an offline core: run code, exact symbolic math, SMT/logic and complexity analysis, with optional gVisor/AppContainer sandboxing.
★ 5
codex-claude-council
Two-model council: ChatGPT (through the Codex CLI) and Claude (through Claude Code) answer independently, then exchange replies until both agree on one answer.
★ 5
copilot-mcp-server
Connect an IDE or AI assistant to GitHub Copilot CLI for code analysis, review and batch processing.
★ 5
ctxfile
Snapshots a project's working state (files, git, plan, decisions) into one context object so a session can move between agents.
★ 5
customgpt-mcp
Access the CustomGPT.ai RAG-as-a-service API.
★ 5
design-token-bridge-mcp
Translates design tokens from Tailwind, CSS, Figma or W3C DTCG into Material 3, SwiftUI, Tailwind config and CSS variables, with WCAG contrast validation.
★ 5
devrecall
Local-first index of your commits, PRs, Jira/Linear tickets, Confluence docs, Slack threads and calendar events to search and cite past work.
★ 5
devutils-mcp-server
Developer utilities: hashing, Base64/hex/URL encoding, UUID and password generation, JWT decoding, JSON/YAML/XML formatting, timestamps, CIDR and text tools.
★ 5
dexio
One wiki that all your agents read and write over MCP, from any machine: search, read, write, edit and move Markdown pages, with every version kept and the
★ 5
dicom-hl7-mcp-server
Bridge DICOM, HL7v2 and FHIR: cross-standard mapping, Mirth Connect channel generation, vendor private tag decoding and integration patterns.
★ 5
Diffcontext
Static-analysis context compiler for Python repos: selects callers, callees and related functions for a change and packs them into a token budget.
★ 5
diffgate
Deterministic guardrail for AI-written diffs: AST-based checks for SQLi, SSRF, XXE, hardcoded secrets and over-abstraction, scoped to the changed lines.
★ 5
DirForge
Read-only directory listing web app: browse directories, read files, search content, inspect archives, compute hashes and check disk usage.
★ 5
dolar-mcp
Argentine exchange rates via DolarAPI (blue, oficial, MEP, CCL, crypto, tarjeta), plus currency conversion and a spread calculator.
★ 5
domain-lookup-mcp
Domain name lookup via RDAP, falling back to WHOIS.
★ 5
editorconfig_mcp
Formats files using .editorconfig rules so AI-generated code follows project formatting standards.
★ 5
enigma-python-mcp
Encrypt and decrypt messages with historically accurate Enigma machine emulators from the enigmapython library.
★ 5
ethics-check-mcp
Ethical analysis of AI conversations: detect bias and harmful content and provide critical-thinking assessments, with automated pattern learning.
★ 5
ezpzfile-mcp
Local document and image tools: read and convert PDF, DOCX, HWP and EML, edit PDFs, resize images, strip EXIF, remove backgrounds and make QR codes.
★ 5
fagan
Autonomous coding pipeline: a frontier model plans and reviews, a local model implements under TDD, and a merge gate re-runs the suite on the rebased branch.
★ 5
flowzap-mcp
Create workflow, sequence and architecture diagrams with the FlowZap Code DSL, with validation, playground links, syntax docs, export, diffing and patching.
★ 5
fmsg-mcp
Give AI agents an address on fmsg, an open federated messaging protocol: inbox, threads, replies, reactions, attachments and waiting for new messages.
★ 5
google-trends-mcp
Google Trends data as JSON: interest over time and by region, plus rising and top related queries and topics for any keyword.
★ 5
graphiti-local
Local temporal knowledge graph with six read-only retrieval tools, Ollama inference, embedded LadybugDB, and a separate human-approved CLI write queue.
★ 5
hipocampo
Bilingual (English/Spanish) dual-memory system on PostgreSQL, pgvector and NVIDIA NIM with progressive retrieval, deduplication, checkpoints and auto-repair.
★ 5
huddo-mcp
Group chat where people and AI agents talk in the same room: join by invite link, read and reply, wait for new messages, and send end-to-end encrypted whispers
★ 5
infrastructure-mcp
Safe, auditable, inventory-driven access to Linux, Docker, Kubernetes, Proxmox, Grafana and Cisco infrastructure through named read-only-by-default tools,
★ 5
iranti
Persistent shared memory for coding agents: facts stored as entity/key/value triples with hybrid semantic search, task checkpoints and conflict resolution.
★ 5
jobd
Self-hostable GPU-aware job broker: dispatch long-running or GPU jobs that outlive the session, route them by VRAM tier and monitor them across sessions.
★ 5
kepil
Accountability layer for AI agents: per-version passports, per-job mandates with spending limits, a fail-closed action gate and a hash-chained journal.
★ 5
LINZA-MCP
Review-gated sidecar for Markdown workspaces: indexes notes into SQLite and proposes links, domains and memory with evidence, editing files only after review.
★ 5
llm-token-tracker
Token usage and cost tracking for OpenAI and Claude APIs with real-time session tracking.
★ 5
local-ydb-toolkit
Operate Docker-based local-ydb deployments locally or over SSH: bootstrap, diagnostics, auth hardening, storage workflows, dump/restore and upgrades.
★ 5
lookacrawler
Token-efficient local web crawler with Playwright-based stealth anti-bot bypass.
★ 5
lore-mcp
Persistent knowledge layer for agents: knowledge base, investigation threads and a journal with multi-agent attribution, on SQLite, PostgreSQL or Supabase.
★ 5
markcrawl
Crawl websites into clean Markdown, search pages and extract structured data with LLMs for web research and RAG pipelines.
★ 5
MarketAuxMcpServer
Market and financial news search with filtering by symbols, industries, countries and date ranges.
★ 5
math-mcp-learning-server
Educational server for math operations, statistics, visualization and persistent workspaces.
★ 5
mcp
Enforces team naming conventions in AI-generated code.
★ 5
mcp
Fundraising for AI agents on Solana: register agents, create campaigns, donate via x402 and track on-chain reputation.
★ 5
mcp-datalink
Secure access to PostgreSQL, MySQL and SQLite databases with parameterized queries and schema inspection.
★ 5
mcp-dolphin
Control the Dolphin GameCube/Wii emulator: memory read/write, GameCube and Wii Remote input, reset, save states and frame advance, via Felk's scripting fork.
★ 5
mcp-firewall
Deterministic security proxy for MCP that intercepts tool calls, enforces YAML policies, scans for secret leakage and logs everything.
★ 5
mcp-graphql-forge
Expose curated GraphQL queries as modular tools via configuration.
★ 5
mcp-itglue
IT Glue, the MSP documentation platform: semantic search over documentation, document and flexible-asset read/write, and role-based access control.
★ 5
mcp-mgba
Control the mGBA Game Boy Advance emulator: memory read/write, button input, screenshots, save states and stepping.
★ 5
mcp-server
Send physical postcards worldwide, individually or in bulk.
★ 5
mcp-server
Manage Uniswap and Aerodrome liquidity positions with leverage, automated rebalancing, and yield optimization on Base, Unichain, and Optimism.
★ 5
mcp-server
Community jury platform where humans and AI agents open cases, weigh evidence and vote together, with arbitration mode, verdict waiting and signed webhooks.
★ 5
mcp-server-logs-sieve
Query, summarize and trace logs in plain English across GCP Cloud Logging, AWS CloudWatch, Azure Log Analytics, Grafana Loki and Elasticsearch.
★ 5
mcp-turboquant
LLM quantization: convert models to GGUF, GPTQ and AWQ, recommend quantization settings, evaluate quality and push to Hugging Face Hub.
★ 5
mcp-websitepublisher-ai
Build and publish websites through conversation: manage pages, assets, entities, records and integrations.
★ 5
mcpbundles
Create custom tool bundles, connect providers with OAuth or API keys, and use one MCP server across many integrations, with a UI for bundles and credentials.
★ 5
media-mcp
Local image and video processing: resize, convert, compress, crop, thumbnails, metadata extraction, rotate, flip, filters and ffmpeg-based video operations.
★ 5
memkin
Local-first personal memory that distills Feishu/Lark chats and Claude Code/Codex sessions into a private knowledge graph of people, projects and tasks.
★ 5
metabase-mcp
Metabase integration: natural-language data analysis, dashboard management, SQL queries and automated insights, with SQL guardrails and audit logging.
★ 5
mockit-mcp
Generate iOS UI mockups as PNG and HTML from a text prompt, using Claude and a headless Playwright renderer.
★ 5
moltrust-mcp-server
Trust infrastructure for AI agents: register DIDs, verify identities, query reputation scores, rate agents and manage W3C Verifiable Credentials.
★ 5
NetLicensing-MCP
Manage the software licensing lifecycle in Labs64 NetLicensing through natural language.
★ 5
nlqueries
Self-hosted natural-language-to-SQL engine with validation for PostgreSQL, MySQL, Snowflake, BigQuery and DuckDB, plus document QA and semantic caching.
★ 5
nodiom-mcp
Read and edit Markdown files by structure (headings, lists, sections) instead of regex or line numbers: read a section, write one list item, append under a
★ 5
NyxDocs
Manage cryptocurrency project documentation across Ethereum, BSC, Polygon and Solana.
★ 5
ocds-mcp
German public procurement data (OCDS): semantic search, tender matching against company profiles and structured filtering.
★ 5
oci-pricing-mcp
Oracle Cloud Infrastructure price data with cost calculators and cross-provider comparisons.
★ 5
offorte-mcp-server
Create and send business proposals with Offorte proposal software.
★ 5
omega-brain-mcp
AI execution pipeline with NAEF logic constraints, VERITAS build gates, semantic vault integration and Tri-Node Cortex validations to curb hallucination.
★ 5
Something missing or broken? Submit a skill or MCP server or tell us.
Setup instructions and compatibility are compiled from publisher docs and community reports, not hands-on testing, unless a step is marked Tested. Check the source before relying on a setup.