- Conduid
- Marketplace
- #python
MCP servers tagged python
10K live MCP servers tagged "python", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with python.
Software Engineering Rl Lab
Reproducible MCP tool-discovery environments for evaluating coding-agent engineering work.
Semantic Runtime
Semantic infrastructure layer for AI Agents: semantic understanding, context resolution, evidence, and safe execution between models and tools.
Agora Backend
Multi-agent LLM debate arena with MCP evidence tools, mechanical fact-checking and blind judging. FastAPI + Bedrock.
Spidey
Production-oriented autonomous coding agent: multi-agent workflows, sandboxed execution, code intelligence, and human approval gates.
ReciboSplit
Splitwise-style app for splitting group expenses, with OpenAI vision-based receipt extraction
Frappe Inspector Support
Documentation, downloads and support for Frappe Inspector
Palimpsest
Local-first, battle-tested, memory that never disappears. Hybrid vector search + knowledge graph + full-text retrieval for AI agents.
Wolf
AI portfolio-management runtime for macOS. Watches obsessively, lacks feelings — the model advises, deterministic code decides. Experimental: paper trading only, not investment ad…
Telegram To Notion
Telegram bot that saves articles to a Notion knowledge base via MCP, with AI summarization and vector search Q&A.
Benn
极简 AI Agent 运行时。~4700 行 Python，3 个外部依赖。认知自由，执行有界——家长行为设限兜底，模型自主决策。
Weather Intelligence System
Agentic weather assistant with MCP server, reasoning agent, and live dashboard — built with FastMCP, OpenAI Agents SDK, and Open-Meteo, deployed on Databricks Apps.
Agent Guard Lite
Runtime security guard for LLM agents and MCP: prompt-injection detection, tool policy enforcement, and SQLite traceability.
Mango
Free-data market providers, historical-context analytics, and a self-grading prediction ledger. Built while learning.
Agent Sbom
Capability-aware SBOM and SARIF scanner for agent skills, MCP manifests, prompts, and scripts.
Liteagent
A native, single-user, local-model-first AI agent. Works with any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio) — full tool-calling loop, MCP client, memory, scheduler, and…
Graph Engineering Course
Hands-on course in agentic graph engineering: temporal knowledge-graph memory for AI agents, driven with Hermes Agent and GitHub Copilot CLI
Evelynn Lite
Watch an agent's memory being built, recalled and forgotten. One page, your own local model, and every memory shows where it came from.
Permitd
Governed tool execution for agent loops: propose -> permit -> approve -> execute -> audit. Fail-closed, zero dependencies.
Agents Should Survive Failure
Durable, governed AI workflows that survive retries and worker crashes without duplicating consequential business effects.
Alpaca Hack
Autonomous paper-trading agent for Alpaca. Trades options and equities on its own: scores news and price signals, sizes by volatility, enforces hard risk limits and flattens intra…
VouqisVerify
Vouqis Verify (VouqisVerify) generates AI Change Evidence Packs from merged GitHub pull requests, with AI change classifications, CI checks, and reviewer evidence exported to Exce…
Pantheon Aiops
Multi-agent AIOps platform in Python, Go and TypeScript — every claim in the docs backed by a test that has been seen to fail
LLM Tool Use Patterns
Production-oriented patterns for LLM agents with tool use in Python. Guard rails, state, observability.
Agent Skill Supply Chain Auditor
Static supply-chain auditor for Agent Skill bundles and MCP configurations with SARIF, Agent-SBOM, and deterministic evaluation.
Contract Driven Agents
A typed agent registry that makes 'the agent claims a tool it doesn't have' structurally impossible — enforced in code, not the prompt.
CyberFortressX
Enterprise Agentic AI SIEM & SOC platform for Palo Alto Firewall analytics, threat intelligence, risk scoring, and automated incident response using FastAPI, IBM Agent Studio and…
Actgate
Local IntentLedger + MCP stdio proxy: propose, approve/deny, hash-chained ledger. Optional HMAC seals.
CurocX VPS Terminal
Bounded, safety-focused VPS terminal connector for AI tool workflows.
Sts2 MCP Bridge
A mod + Python/MCP bridge that lets an agent read Slay the Spire 2 state and play it. Deterministic autopilot, no LLM in the loop.
Mini Coding Agent
A minimal Python coding agent with tool calling, sandboxed execution, test-driven feedback, verification gates, token budgets, and optional Skill/MCP support.
Operator Etl
Agentic ETL pipeline for FOIA & public comments — LangGraph, MCP, PII vault, Medallion warehouse (DuckDB/BigQuery)
Marlow
内部 IT 工单 Agent（个人 PoC）：自然语言查 / 关单，改权限须人批；成功看工单库和审计。
Jarvis Rag Local
Local-first GraphRAG over a markdown knowledge base: LightRAG, Ollama/Qwen, MCP server, LLM router, scheduled self-maintenance
Zhoda
Open-source LLM deliberation and decision-review engine with a Python CLI and MCP server. Includes minority reports and auditable transcripts.
AI Agent Channel
A mailbox for coding agents where a message can be a debt
Dewie
Agent-native retrieval over a self-enriching corpus: hybrid search + graph navigation exposed as MCP tools, so small models can punch above their weight.
Aether Agentic Workspace
Full-stack AI assistant with hybrid-retrieval RAG (pgvector + BM25 + cross-encoder rerank), a provider-agnostic LLM backend, MCP and Google Workspace tool use, and a LiveKit voice…
Airi Pc Bootstrap
Public Computer Mode runtime and reproducible bootstrap for Airi-PC, with a Windows Companion for end users.
Transcript Bridge
Move agent transcripts between providers without losing data.
Support Ticket Triage Assistant
Portfolio: GitHub-first agentic SDLC case study (v0.1). Demo app: synthetic support-ticket triage. Start: docs/00_project/PORTFOLIO_TOUR.md
CodeBrowser
CodeBrowser with Ollama Integrations
CortexIQ AI
CortexIQ AI is an open platform that make AI more useful, reliable, transparent, and controllable.
Spooky Action
Computer use on a Mac for any AI agent. It presses the button, not a pixel — through the accessibility layer, so your cursor never moves. Watch it work, and take the screen back b…
EduAgent
Autonomous AI agent that automates academic admin for university professors — course planning, PFE tracking, and student email triage ,RAG-based student FAQ chatbot
Stealth Startup Filesystem Agent
Stealth Startup reference agent: OpenAI Agents SDK assistant that reads local files through the MCP filesystem server, hardened for sandboxed runs
Langgraph Crewai MCP Orchestrator
A production-grade monorepo architecture demonstrating multi-agent system orchestration. Uses LangGraph as the deterministic control plane, CrewAI for agent reasoning, and FastMCP…
Live Docs MCP
Real-time documentation MCP server for AI engineers - fetch live docs for 45+ libraries (LangChain, OpenAI, Anthropic, CrewAI, Qdrant and more) directly inside Claude. No stale tr…
Infinity Scraper
High-Performance Dynamic Web Scraping, Headless SPA Rendering & OSINT Intelligence MCP Server for AI Agents.
vishalbanwari26/mnemos
deleted. Real before/after MCP eval: +60% answer accuracy with memory vs. without. `git clone` + `uv sync` (not yet on PyPI).
dkaleganov/mercury-multiorg-mcp
filing check. Every call names its organization, account numbers are masked, and nothing in the code can move money.