{"id":26127736,"url":"https://github.com/dylibso/mcpx-eval","last_synced_at":"2025-03-10T18:36:19.394Z","repository":{"id":280508823,"uuid":"940933795","full_name":"dylibso/mcpx-eval","owner":"dylibso","description":"An open-ended eval framework for mcp.run tools","archived":false,"fork":false,"pushed_at":"2025-03-03T19:54:50.000Z","size":208,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-03T20:35:52.228Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dylibso.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-01T04:52:04.000Z","updated_at":"2025-03-03T19:55:04.000Z","dependencies_parsed_at":"2025-03-03T20:46:08.564Z","dependency_job_id":null,"html_url":"https://github.com/dylibso/mcpx-eval","commit_stats":null,"previous_names":["dylibso/mcpx-eval"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dylibso%2Fmcpx-eval","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dylibso%2Fmcpx-eval/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dylibso%2Fmcpx-eval/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dylibso%2Fmcpx-eval/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dylibso","download_url":"https://codeload.github.com/dylibso/mcpx-eval/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242903345,"owners_count":20204254,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-03-10T18:36:18.884Z","updated_at":"2025-03-10T18:36:19.386Z","avatar_url":"https://github.com/dylibso.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# mcpx-eval\n\nA framework for evaluating open-ended tool use across various large language models.\n\n`mcpx-eval` can be used to compare the output of different LLMs with the same prompt for a given task using [mcp.run](https://www.mcp.run) tools.\nThis means we're not only interested in the quality of the output, but also curious about the helpfulness of various models\nwhen presented with real world tools.\n\n## Test configs\n\nThe [tests/](https://github.com/dylibso/mcpx-eval/tree/main/tests) directory contains pre-defined evals\n\n## Installation\n\n```bash\nuv tool install git+https://github.com/dylibso/mcpx-eval\n```\n\n## Usage\n\nRun the `my-test` test for 10 iterations:\n\n```bash\nmcpx-eval test --model ... --model ... --config my-test.toml --iter 10\n```\n\nGenerate an HTML scoreboard for all evals:\n\n```bash\nmcpx-eval gen --html results.html --show\n```\n\n### Test file\n\nA test file is a TOML file containing the following fields:\n\n- `name` - name of the test\n- `prompt` - prompt to test, this is passed to the LLM under test\n- `check` - prompt for the judge, this is used to determine the quality of the test output \n- `expected-tools` - list of tool names that might be used\n- `ignore-tools` - list of tools to ignore, they will not be available to the LLM\n- `import` - includes fields from another test TOML file\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdylibso%2Fmcpx-eval","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdylibso%2Fmcpx-eval","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdylibso%2Fmcpx-eval/lists"}