Skip to main content
Glama
304,864 tools. Last updated 2026-07-21 16:01

"LangGraph" matching MCP tools:

  • Execute a LangGraph-powered NestJS agent for processing user requests. Optionally select between OpenAI or Ollama providers and customize the model.
  • Convert a JSON agent trace into an EvalCase payload for immediate scoring without re-running the agent. Supports LangGraph, OpenAI Agents, and manual frameworks.
    Apache 2.0
  • Adds ioa-observe-sdk instrumentation to Python AI agent files, inserting Observe.init(), SDK imports, and decorators for LlamaIndex, LangGraph, CrewAI, and OpenAI SDK agents, while backing up the original file.
    Apache 2.0
  • Statically analyze LLM-agent workflows to identify runaway budget risks and missing token caps before deployment. Get a worst-case budget summary with pass/fail verdict.
    MIT

Matching MCP Servers

  • Audit multi-agent system communications to detect infinite delegation loops, privilege escalation, data leakage, and unauthorized handoffs across protocols like A2A, CrewAI, LangGraph, and AutoGen.
    Apache 2.0
  • Scan files or directories for AI agent security vulnerabilities including prompt injection, infinite loops, and token bombing. Supports 20+ agent frameworks.
    Apache 2.0
  • Connects to a new agent server, such as Mastra or LangGraph, and adds it to the proxy's server list for dynamic agent discovery.
    MIT
  • Search curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only examples covering those principles), difficulty (beginner/intermediate/advanced), library (e.g. 'langgraph', 'openai'). Returns each match's slug, title, summary, principle coverage, difficulty, library, and source-code link — slug is the handle examples.get hydrates. Default limit 5, capped server-side. Use this when the user describes a use case, technique, or library and wants matching examples; prefer examples.get when you already have the slug; prefer guides.search when the user wants a full walkthrough; prefer principles.search when the user wants doctrine guidance, not an implementation.
    Connector
  • Search curated examples by free-text query, ranked by relevance, with optional filters: principle_ids (only examples covering those principles), difficulty (beginner/intermediate/advanced), library (e.g. 'langgraph', 'openai'). Returns each match's slug, title, summary, principle coverage, difficulty, library, and source-code link — slug is the handle examples.get hydrates. Default limit 5, capped server-side. Use this when the user describes a use case, technique, or library and wants matching examples; prefer examples.get when you already have the slug; prefer guides.search when the user wants a full walkthrough; prefer principles.search when the user wants doctrine guidance, not an implementation.
    Connector
  • Returns Mastra (Bun) and LangGraph (Python) patterns for AI agent workflows. Call this BEFORE create_workflow / update_draft when building chatbots, tool-using agents, or multi-step LLM flows. Do not hand-roll custom agent loops — use the preinstalled frameworks.
    Connector
  • Create a workflow. The workflow ID (UUID) is assigned automatically. For AI agent workflows, call get_agent_framework_docs first and use Mastra (bun) or LangGraph (python).
    Connector
  • Generate the install + client config for an MCP server in a given runtime (claude-desktop, cursor, vscode, windsurf, cline, continue, goose, openai-agents, langgraph, crewai).
    Connector