# MCP-Universe

> Salesforce AI Research benchmark and framework that evaluates LLMs and agents on real-world tasks against live MCP servers, with a public leaderboard.

- id: `mcp-universe`
- category: Information (`information`)
- url: https://mcp-universe.github.io/
- repo: https://github.com/SalesforceAIResearch/MCP-Universe
- docs: https://github.com/SalesforceAIResearch/MCP-Universe#readme
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: benchmark, mcp, agent-evaluation, leaderboard, tool-use
- related: MCPMark (https://indexagentica.com/entries/mcpmark/); Berkeley Function Calling Leaderboard (BFCL) (https://indexagentica.com/entries/bfcl/); τ-bench (tau2-bench) (https://indexagentica.com/entries/tau-bench/); GAIA (https://indexagentica.com/entries/gaia-benchmark/)
- sources: https://github.com/SalesforceAIResearch/MCP-Universe , https://mcp-universe.github.io/ , https://arxiv.org/abs/2508.14704
- added: 2026-10-18
- updated: 2026-10-18
- last verified: 2026-10-18
- featured in: Agent benchmarks compared (https://indexagentica.com/compare/agent-benchmarks/)
- maintainer: Salesforce AI Research
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/mcp-universe/
- json: https://indexagentica.com/api/entries/mcp-universe.json

Domains include web search, location navigation, browser automation, financial analysis, repository management and 3D design, stressing long-horizon reasoning, large unfamiliar tool spaces and time-sensitive ground truth. The framework also runs the MCPMark tasks and ships agent tooling (MCP+ context wrapper, a deep-research agent). Paper: arXiv 2508.14704.