Skip to main content
Glama
521,454 tools. Updated 2026-09-06 11:20

"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
  • Resume an interrupted research campaign by collecting missing sites with fresh angles, preventing duplicate runs and stopping when complete.
    MIT

Matching MCP Servers

Matching MCP Connectors

  • 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
  • Scan a Terraform plan JSON to identify security issues, receive severity ratings, suggested fixes, and corpus citations for remediation.
    Apache 2.0
  • 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
  • Generate production-ready RAG architecture blueprints with vector DBs (ChromaDB, Qdrant, Pinecone), local LLMs (Ollama, vLLM), and LangGraph/LangChain orchestration for any target use case.
    MIT
  • 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
  • Run a document and video discovery workflow using a query. Retrieves and combines results from multiple sources including Supabase, web search, and YouTube.
    MIT
  • Answer sales performance questions by querying a live database. Detect revenue drops and anomalies, with human review for escalated issues.
    -