{
  "listings": [
    {
      "slug": "claude-agent-sdk",
      "name": "Claude Agent SDK",
      "company": "Anthropic, PBC",
      "grade": "BB",
      "fit": "yes",
      "why": "stdio, HTTP, SSE and in-process servers at once, tools namespaced mcp__server__tool, headers set per query, and the init message reports each server as connected, pending, failed or needs-auth. Measured connect time is the suite's.",
      "source": "https://code.claude.com/docs/en/agent-sdk/mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/claude-agent-sdk"
    },
    {
      "slug": "agno",
      "name": "Agno",
      "company": "Agno Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "MCPTools and MultiMCPTools take stdio, streamable HTTP and SSE, tool_name_prefix avoids clashes, and header_provider sets headers before each run. How a server that fails to connect is reported to the host isn't shown on the pages read.",
      "source": "https://docs.agno.com/tools/mcp/multiple-servers.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/agno"
    },
    {
      "slug": "boxlang-ai",
      "name": "BoxLang AI",
      "company": "Ortus Solutions, Corp.",
      "grade": "B",
      "fit": "caveat",
      "why": "mcpServers takes HTTP and stdio servers with a prefix against clashes, headers, bearer and OAuth. A server that fails to start is only written to the ai log and the agent carries on, so the host isn't told; the stdio allow-list is open by default.",
      "source": "https://ai.ortusbooks.com/main-components/agents/tools-and-mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/boxlang-ai"
    },
    {
      "slug": "crewai",
      "name": "CrewAI",
      "company": "CrewAI, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "MCPServerAdapter aggregates stdio, SSE and streamable HTTP servers at once, but the page shows no tool-name prefix for clashes or per-run headers, and a failed server raises from the context manager.",
      "source": "https://docs.crewai.com/v1.15.41/en/mcp/multiple-servers.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/crewai"
    },
    {
      "slug": "cursor-agent-sdk",
      "name": "Cursor Agent SDK",
      "company": "Anysphere, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Connections reach HTTP and stdio servers, with credential templates in headers and a per-session auth callback for HTTP. An account found servers needing approval vanish from the SDK with no event (forum 178033).",
      "source": "https://cursor.com/docs/agent-sdk/reference/connections.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cursor-agent-sdk"
    },
    {
      "slug": "docker-agent",
      "name": "Docker Agent",
      "company": "Docker, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "The mcp toolset takes local stdio, Docker MCP catalog and remote streamable HTTP or SSE servers, with OAuth handled automatically. The page shows no tool-name prefix for clashes or per-run headers for many users.",
      "source": "https://docker.github.io/docker-agent/tools/mcp/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/docker-agent"
    },
    {
      "slug": "google-adk",
      "name": "Agent Development Kit (ADK)",
      "company": "Google LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "McpToolset takes stdio and HTTP connections with tool_filter. The MCP page read shows no name-prefix option, per-user headers or failure reporting, and the listing notes no error handling on the page.",
      "source": "https://adk.dev/tools-custom/mcp-tools/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/google-adk"
    },
    {
      "slug": "guilds-run",
      "name": "guilds.run",
      "company": "Cigale AI",
      "grade": "C",
      "fit": "caveat",
      "why": "Connectors are remote MCP endpoints signed in per organisation, guild or agent with token or OAuth, plus custom headers. Only remote HTTPS endpoints are described, configured in the app rather than per run in code.",
      "source": "https://docs.guilds.run/tools-and-connectors/connectors",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/guilds-run"
    },
    {
      "slug": "langgraph",
      "name": "LangGraph",
      "company": "LangChain, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "LangChain's MCP adapter connects several servers, prefixes each tool with its config key and mixes stdio and HTTP; the listing records langchain.mcp as beta. Failure reporting to the host isn't described on the connections page.",
      "source": "https://docs.langchain.com/oss/python/langchain/mcp/connections.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/langgraph"
    },
    {
      "slug": "llamaindex",
      "name": "LlamaIndex Framework",
      "company": "LlamaIndex, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "MCP tools load from existing servers into workflows and workflows can be served as MCP. The guide read gives no name-clash handling or failure reporting, and an account found no hook to set tool inputs from the authenticated user (#20386).",
      "source": "https://developers.llamaindex.ai/python/framework/module_guides/mcp/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/llamaindex"
    },
    {
      "slug": "mastra",
      "name": "Mastra",
      "company": "Kepler Software, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "MCPClient connects several servers; listTools() prefixes tools with the server name, but the per-user listToolsets() path uses raw names that can collide. Headers and OAuth are supported; how unreachable servers are reported to the host wasn't shown.",
      "source": "https://mastra.ai/docs/connections/mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/mastra"
    },
    {
      "slug": "microsoft-agent-framework",
      "name": "Microsoft Agent Framework",
      "company": "Microsoft Corporation",
      "grade": "A",
      "fit": "caveat",
      "why": "MCPStdioTool and MCPStreamableHTTPTool connect local and remote servers, headers can be set per run or through a header_provider, and approval_mode applies to MCP tools. Name-clash handling and failure reporting weren't shown on the page.",
      "source": "https://learn.microsoft.com/en-us/agent-framework/agents/tools/local-mcp-tools",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/microsoft-agent-framework"
    },
    {
      "slug": "nitrostack",
      "name": "NitroStack",
      "company": "Nitrostack Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Covers the reverse case: exposing the team's tools as an MCP server over STDIO and HTTP, with guards for JWTs and API keys. It is not an MCP client, so an agent can't use it to call other servers.",
      "source": "https://docs.nitrostack.ai/docs/getting-started/how-nitrostack-works.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/nitrostack"
    },
    {
      "slug": "openai-agents-sdk",
      "name": "OpenAI Agents SDK",
      "company": "OpenAI OpCo, LLC",
      "grade": "AA",
      "fit": "caveat",
      "why": "Hosted, streamable HTTP, SSE and stdio servers; include_server_in_tool_names prefixes tools (opt-in); failed servers are dropped and tracked in failed_servers with reconnect(). Headers are set when a server is created, so per-user auth (#1969) still needs one connection per user.",
      "source": "https://openai.github.io/openai-agents-python/mcp/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/openai-agents-sdk"
    },
    {
      "slug": "pydantic-ai",
      "name": "Pydantic AI",
      "company": "Pydantic Services Inc.",
      "grade": "AA",
      "fit": "caveat",
      "why": "MCPToolset takes Streamable HTTP, SSE and stdio, .prefixed() avoids name clashes, tool errors go back to the model as ModelRetry by default, and headers or a custom http_client are set per toolset. An account hit a cancel-scope error with concurrency above one (pydantic-ai #2818).",
      "source": "https://pydantic.dev/docs/ai/mcp/client/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/pydantic-ai"
    },
    {
      "slug": "smolagents",
      "name": "smolagents",
      "company": "Hugging Face, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "MCPClient loads tools from stdio or streamable HTTP servers, including several at once. The tools page shows no name-prefix option, per-run headers or failure reporting.",
      "source": "https://huggingface.co/docs/smolagents/v1.26.0/tutorials/tools.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/smolagents"
    },
    {
      "slug": "strands-agents",
      "name": "Strands Agents",
      "company": "Amazon Web Services, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "MCPClient takes stdio and streamable HTTP (including OAuth or IAM), prefix_with_server_name for clashes, and tool_filters. Per-run headers and failure reporting weren't shown on the page.",
      "source": "https://strandsagents.com/docs/user-guide/sdk/tools/mcp-tools/index.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/strands-agents"
    },
    {
      "slug": "vercel-ai-sdk",
      "name": "AI SDK",
      "company": "Vercel Inc.",
      "grade": "AA",
      "fit": "caveat",
      "why": "createMCPClient supports HTTP (recommended), SSE and stdio (local only), with headers in the transport. No name-prefix option for clashes appeared on the page, and an open account says prepareStep can't change the tool list per step (vercel/ai #9743).",
      "source": "https://ai-sdk.dev/docs/ai-sdk-core/mcp-tools",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vercel-ai-sdk"
    },
    {
      "slug": "agentos",
      "name": "AgentOS",
      "company": "Framers Lab, Inc.",
      "grade": "A",
      "fit": "no",
      "why": "No MCP client page in the docs sitemap or llms.txt; tools come from the app, extensions or the forge.",
      "source": "https://docs.agentos.sh/llms.txt",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/agentos"
    },
    {
      "slug": "tradingagents",
      "name": "TradingAgents",
      "company": "Tauric Research",
      "grade": "B",
      "fit": "no",
      "why": "No MCP client or server; it is driven through Python or the CLI.",
      "source": "https://raw.githubusercontent.com/TauricResearch/TradingAgents/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tradingagents"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 9,
    "after": [
      "frameworks.tool-calling-agent"
    ],
    "area": "frameworks",
    "asks": [
      "connect the GitHub MCP server to my agent",
      "use these MCP servers from my Python agent",
      "add per-user auth to the MCP calls",
      "load tools from MCP as needed"
    ],
    "before": [
      "agent-auth.connect-user-account"
    ],
    "blockers": [
      "two servers exposing the same tool name stop the agent",
      "headers fixed at start-up, so one server connection cannot serve many users",
      "no hook to set tool arguments from the authenticated user before a call",
      "long MCP tasks deleted by a TTL while still working",
      "no MCP client at all in some listings"
    ],
    "capabilities": [
      "agent.framework",
      "agent.mcp-client",
      "mcp.server"
    ],
    "category": "frameworks",
    "categoryName": "Agent frameworks \u0026 SDKs",
    "checked": "2026-11-15",
    "companies": {
      "fit": 1,
      "fitWithLimit": 17,
      "tagged": 93
    },
    "competition": "one",
    "fits": [
      "claude-agent-sdk"
    ],
    "fitsWithLimit": [
      "agno",
      "boxlang-ai",
      "crewai",
      "cursor-agent-sdk",
      "docker-agent",
      "google-adk",
      "guilds-run",
      "langgraph",
      "llamaindex",
      "mastra",
      "microsoft-agent-framework",
      "nitrostack",
      "openai-agents-sdk",
      "pydantic-ai",
      "smolagents",
      "strands-agents",
      "vercel-ai-sdk"
    ],
    "id": "frameworks.mcp-tools",
    "listings": {
      "caveat": 17,
      "no": 2,
      "notRead": 0,
      "tagged": 104,
      "unchecked": 0,
      "yes": 1
    },
    "name": "Give an agent tools from MCP servers",
    "status": "draft",
    "success": "The agent lists and calls tools from two or more MCP servers at once, with name clashes handled, auth headers set per run or per user, tool errors passed to the model instead of crashing the run, and servers that fail to connect or need approval reported to the host. Measured: connect time for 3 servers and run success with concurrency above one.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/frameworks.mcp-tools.json",
    "weight": 12,
    "weightBasis": "7 of 61 accounts have this as their main job (share 11.5, rounded by largest remainder to sum 100)"
  }
}
