Atla MCP Server

Created By
spisupata year ago
Initial version of an mcp server for agents to interact with atla's models
Overview

What is Atla MCP Server?

Atla MCP Server is an implementation of a Model Control Protocol (MCP) server that provides a standardized interface for large language models (LLMs) to interact with the Atla SDK and utilize state-of-the-art evaluation models.

How to use Atla MCP Server?

To use Atla MCP Server, clone the repository, install the necessary dependencies, set up your environment variables with your Atla API key, and run the server with your desired configuration. You can integrate it with OpenAI agents or other compatible systems.

Key features of Atla MCP Server?

  • Evaluate individual responses with Selene 1.
  • Run batch evaluations with Selene 1.
  • List available evaluation metrics, create new ones, or fetch them by name.

Use cases of Atla MCP Server?

  1. Enhancing the quality of responses generated by AI agents.
  2. Evaluating and improving the performance of language models.
  3. Integrating with various AI frameworks and tools for better evaluation metrics.

FAQ from Atla MCP Server?

  • What is Selene 1?

Selene 1 is the evaluation model used by Atla MCP Server to assess the quality of responses.

  • Is Atla MCP Server free to use?

Yes, Atla MCP Server is open-source and free to use.

  • Can I use Atla MCP Server with other AI models?

Yes, it is designed to work with various LLMs and can be integrated into different AI frameworks.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
spisupat
Star
0
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago