MCP Servers tools for LangChain / LangGraph

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Seven-package, multi-language (Python, Rust, TypeScript, Go, .NET) runtime security toolkit that addresses all 10 OWASP Agentic AI risks with deterministic, sub-millisecond policy enforcement. Includes Agent OS (policy engine intercepting every action), Agent Mesh (secure agent-to-agent communication), and Agent Runtime (dynamic execution rings). Hooks into LangChain callbacks, CrewAI task decorat

Memory service with semantic search, persistent storage and autonomous memory consolidation

Local RAG (on-premises) with MCP server

MCP gateway & OAuth MCP servers. LangGraph agent: memory, eval/tracking, PII guard, context trimming. Docker quick start for enterprise agents.

A local-first inbox for long-running AI agents, built with DeepAgents and LangGraph.

AegisOps企业信息系统智能运维平台：自动巡检、Agent 故障排查、证据工单与审批处置。LangGraph · Deep Agents · MCP；附可复现实测记录。

Open-source memory infrastructure for AI agents. Provides semantic (entities/facts), episodic (conversations), and procedural (learned behaviors) memory with auto-reflection. Python SDK, JS SDK, MCP server, and REST API

Search Bilibili content, with LangChain integration examples

Selects the schema objects a SQL agent sees and returns only the tables the calling principal may read, on Postgres, Oracle, MySQL and SQL Server

Multi-agent orchestration with a race-condition-safe shared blackboard, agent spawning, FSM transitions, budget and token tracking, and audit logs

Convert, merge, redact, sign, OCR, watermark and extract data from PDFs and Office documents via the Nutrient DWS Processor API

Access Mattermost teams, channels and messages, plus an MCP host running as a Mattermost bot that can use configured MCP servers

Deterministic AI safety policy engine with Z3 formal verification: write, verify and enforce machine-verifiable constraints for AI agents

Unified MCP platform that connects many apps, tools and services behind one interface

Turns any Swagger/OpenAPI REST endpoint with a yaml/json definition into an MCP Server with Langchain/Langflow integration automatically

Policy-based governance for agent tool calls across LangChain, OpenAI, Anthropic and MCP: YAML policies, approval gates, risk assessment and audit logging

The approval and accountability layer for AI agents. Identity → Policy → Approval → Trace. 13 framework integrations. Free during early access

Coherence guard for shared files: when two agents write the same file, the stale writer is denied instead of overwriting, then reacquires and retries

Local privacy testing for AI agents: scan code for PII and secrets, score execution traces across internal channels, redact text, and track new or fixed findings through MCP tools

Web search across DuckDuckGo, Bing, Google (via SerpAPI) and Tavily with automatic rate limiting, caching and multi-language support

Local retrieval over ISTQB, OWASP, IEEE, ISO and EU AI Act QA standards, plus QA effort estimation, QA document review and JUnit/CSV flakiness analysis

Data quality checks on DuckDB, BigQuery, Athena, Databricks and Postgres, with LLM root-cause analysis of failures and proposed SQL remediations

L402 SDK for TypeScript, Python, Go and Rust: server middleware, an auto-paying agent client, an MCP server, LangChain integration and budget control

EU AI Act compliance scanner for Python AI agents (LangChain, CrewAI, AutoGen, OpenAI) with prompt injection detection, risk classification and fix generation

Mercado Pago payments for LATAM merchants: create payment links, search payments and issue refunds

Drive an iPhone or iOS Simulator via XCUIAutomation and WebDriverAgent, with compact screen digests and confirmation before destructive actions

Non-custodial Solana trading engine: swaps, limit, trailing, TWAP and DCA orders across Raydium, PumpSwap, Orca and Meteora with Jito MEV protection

Corporate debt structure data: search issuers and bonds with leverage ratios, seniority, covenants, guarantor chains and FINRA TRACE prices

Shared versioned state store with optimistic concurrency control for coordinating concurrent agents, plus SQLite-backed claim/release locks and an audit log

TRON Energy and Bandwidth marketplace and DEX swap aggregator: buy energy, sell resources and swap TRC-20 tokens via SunSwap

RAG over PDFs, YouTube videos, GitHub repos and Discord exports: index documents and query them with citations

Visual, multimodal web scraping without CSS selectors, plus phishing and crypto drainer detection

Business identity data: company verification, VAT, BORME, GLEIF, ownership and risk signals across many countries

Tenant-bound agent spend authorization: policy guardrails, spend intents, evidence, escrow settlement, completion validation and portable receipts

Register LLMs and agents and submit Markdown research papers to the BenchClaw leaderboard, where a panel of judges scores them with deception detectors

Discover, preview and buy live agent data APIs (vendor risk, company intelligence, transaction preflight, EVM reads), paying via x402 in USDC on Base

Run queries against Memgraph and access its schema

Safety checks before paying x402 endpoints: liveness, scam scans (payTo hijack, honeypot), on-chain receiver verification and trust scores

Manage images and annotations in the Image Label annotation tool (histopathology, microscopy): bulk upload, annotation clean-up and COCO/YOLO dataset export

x402 pay-per-call tools: token rug and honeypot checks, new-pair and whale-swap signals, SEO/GEO audits, web extraction, link previews and LLM inference

Capture websites as PNG, JPEG, WebP or PDF with device emulation, dark mode, ad blocking and cookie banner removal

FastMCP server for business intelligence and data agents, exposing dynamic KPI analytics, anomaly detection, and schema resources across 10 business domains via stdio and SSE transports