{"id":27671524,"url":"https://github.com/atla-ai/atla-mcp-server","last_synced_at":"2025-04-24T23:37:00.324Z","repository":{"id":288084573,"uuid":"963194434","full_name":"atla-ai/atla-mcp-server","owner":"atla-ai","description":"An MCP server implementation providing a standardized interface for LLMs to interact with the Atla API.","archived":false,"fork":false,"pushed_at":"2025-04-22T13:03:29.000Z","size":46,"stargazers_count":2,"open_issues_count":2,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-22T14:23:03.751Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://docs.atla-ai.com","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/atla-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":null,"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,"zenodo":null}},"created_at":"2025-04-09T09:55:33.000Z","updated_at":"2025-04-17T13:12:02.000Z","dependencies_parsed_at":"2025-04-15T13:48:15.748Z","dependency_job_id":"48bbe72b-4f31-4890-8bb9-dc4499e52768","html_url":"https://github.com/atla-ai/atla-mcp-server","commit_stats":null,"previous_names":["atla-ai/atla-mcp-server"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atla-ai%2Fatla-mcp-server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atla-ai%2Fatla-mcp-server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atla-ai%2Fatla-mcp-server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atla-ai%2Fatla-mcp-server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atla-ai","download_url":"https://codeload.github.com/atla-ai/atla-mcp-server/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250729110,"owners_count":21477606,"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":"2025-04-24T23:36:59.280Z","updated_at":"2025-04-24T23:37:00.310Z","avatar_url":"https://github.com/atla-ai.png","language":"Python","funding_links":[],"categories":["📦 Other","Official Servers","Other Tools and Integrations","Data Analytics","AI Agent Frameworks"],"sub_categories":["How to Submit"],"readme":"# Atla MCP Server\n\nAn MCP server implementation providing a standardized interface for LLMs to interact with the Atla API for state-of-the-art LLMJ evaluation.\n\n\u003e Learn more about Atla [here](https://docs.atla-ai.com). Learn more about the Model Context Protocol [here](https://modelcontextprotocol.io).\n\n\u003ca href=\"https://glama.ai/mcp/servers/@atla-ai/atla-mcp-server\"\u003e\n  \u003cimg width=\"380\" height=\"200\" src=\"https://glama.ai/mcp/servers/@atla-ai/atla-mcp-server/badge\" alt=\"Atla MCP server\" /\u003e\n\u003c/a\u003e\n\n## Available Tools\n\n- `evaluate_llm_response`: Evaluate an LLM's response to a prompt using a given evaluation criteria. This function uses an Atla evaluation model under the hood to return a dictionary containing a score for the model's response and a textual critique containing feedback on the model's response.\n- `evaluate_llm_response_on_multiple_criteria`: Evaluate an LLM's response to a prompt across _multiple_ evaluation criteria. This function uses an Atla evaluation model under the hood to return a list of dictionaries, each containing an evaluation score and critique for a given criteria.\n\n## Usage\n\n\u003e To use the MCP server, you will need an Atla API key. You can find your existing API key [here](https://www.atla-ai.com/sign-in) or create a new one [here](https://www.atla-ai.com/sign-up).\n\n### Installation\n\n\u003e We recommend using `uv` to manage the Python environment. See [here](https://docs.astral.sh/uv/getting-started/installation/) for installation instructions.\n\n### Manually running the server\n\nOnce you have `uv` installed and have your Atla API key, you can manually run the MCP server using `uvx` (which is provided by `uv`):\n\n```bash\nATLA_API_KEY=\u003cyour-api-key\u003e uvx atla-mcp-server\n```\n\n### Connecting to the server\n\n\u003e Having issues or need help connecting to another client? Feel free to open an issue or [contact us](mailto:support@atla-ai.com)!\n\n#### OpenAI Agents SDK\n\n\u003e For more details on using the OpenAI Agents SDK with MCP servers, refer to the [official documentation](https://openai.github.io/openai-agents-python/).\n\n1. Install the OpenAI Agents SDK:\n\n```shell\npip install openai-agents\n```\n\n2. Use the OpenAI Agents SDK to connect to the server:\n\n```python\nimport os\n\nfrom agents import Agent\nfrom agents.mcp import MCPServerStdio\n\nasync with MCPServerStdio(\n        params={\n            \"command\": \"uvx\",\n            \"args\": [\"atla-mcp-server\"],\n            \"env\": {\"ATLA_API_KEY\": os.environ.get(\"ATLA_API_KEY\")}\n        }\n    ) as atla_mcp_server:\n    ...\n```\n\n#### Claude Desktop\n\n\u003e For more details on configuring MCP servers in Claude Desktop, refer to the [official MCP quickstart guide](https://modelcontextprotocol.io/quickstart/user).\n\n1. Add the following to your `claude_desktop_config.json` file:\n\n```json\n{\n  \"mcpServers\": {\n    \"atla-mcp-server\": {\n      \"command\": \"uvx\",\n      \"args\": [\"atla-mcp-server\"],\n      \"env\": {\n        \"ATLA_API_KEY\": \"\u003cyour-atla-api-key\u003e\"\n      }\n    }\n  }\n}\n```\n\n2. **Restart Claude Desktop** to apply the changes.\n\nYou should now see options from `atla-mcp-server` in the list of available MCP tools.\n\n#### Cursor\n\n\u003e For more details on configuring MCP servers in Cursor, refer to the [official documentation](https://docs.cursor.com/context/model-context-protocol).\n\n1. Add the following to your `.cursor/mcp.json` file:\n\n```json\n{\n  \"mcpServers\": {\n    \"atla-mcp-server\": {\n      \"command\": \"uvx\",\n      \"args\": [\"atla-mcp-server\"],\n      \"env\": {\n        \"ATLA_API_KEY\": \"\u003cyour-atla-api-key\u003e\"\n      }\n    }\n  }\n}\n```\n\nYou should now see `atla-mcp-server` in the list of available MCP servers.\n\n## Contributing\n\nContributions are welcome! Please see the [CONTRIBUTING.md](CONTRIBUTING.md) file for details.\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatla-ai%2Fatla-mcp-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatla-ai%2Fatla-mcp-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatla-ai%2Fatla-mcp-server/lists"}