Skip to main content
Glama
enesjakozh
atla-ai

Atla

Official
by atla-ai
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Atla MCP Server

CAUTION

This repository was archived on July 21, 2025. The Atla API is no longer active.

An MCP server implementation providing a standardized interface for LLMs to interact with the Atla API for state-of-the-art LLMJ evaluation.

Learn more about Atla here. Learn more about the Model Context Protocol here.

Available Tools

  • 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.

  • 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.

Related MCP server: Ollama MCP Server

Usage

To use the MCP server, you will need an Atla API key. You can find your existing API key here or create a new one here.

Installation

We recommend using uv to manage the Python environment. See here for installation instructions.

Manually running the server

Once you have uv installed and have your Atla API key, you can manually run the MCP server using uvx (which is provided by uv):

ATLA_API_KEY=<your-api-key> uvx atla-mcp-server

Connecting to the server

Having issues or need help connecting to another client? Feel free to open an issue or contact us!

OpenAI Agents SDK

For more details on using the OpenAI Agents SDK with MCP servers, refer to the official documentation.

  1. Install the OpenAI Agents SDK:

pip install openai-agents

  1. Use the OpenAI Agents SDK to connect to the server:

import os

from agents import Agent
from agents.mcp import MCPServerStdio

async with MCPServerStdio(
        params={
            "command": "uvx",
            "args": ["atla-mcp-server"],
            "env": {"ATLA_API_KEY": os.environ.get("ATLA_API_KEY")}
        }
    ) as atla_mcp_server:
    ...

Claude Desktop

For more details on configuring MCP servers in Claude Desktop, refer to the official MCP quickstart guide.

  1. Add the following to your claude_desktop_config.json file:

{
  "mcpServers": {
    "atla-mcp-server": {
      "command": "uvx",
      "args": ["atla-mcp-server"],
      "env": {
        "ATLA_API_KEY": "<your-atla-api-key>"
      }
    }
  }
}

  1. Restart Claude Desktop to apply the changes.

You should now see options from atla-mcp-server in the list of available MCP tools.

Cursor

For more details on configuring MCP servers in Cursor, refer to the official documentation.

  1. Add the following to your .cursor/mcp.json file:

{
  "mcpServers": {
    "atla-mcp-server": {
      "command": "uvx",
      "args": ["atla-mcp-server"],
      "env": {
        "ATLA_API_KEY": "<your-atla-api-key>"
      }
    }
  }
}

You should now see atla-mcp-server in the list of available MCP servers.

Contributing

Contributions are welcome! Please see the CONTRIBUTING.md file for details.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Available Tools

2 tools
evaluate_llm_responseA

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.

Returns:
    dict[str, str]: A dictionary containing the evaluation score and critique, in
        the format `{"score": <score>, "critique": <critique>}`.
ParametersJSON Schema
NameRequiredDescriptionDefault
evaluation_criteriaYesThe specific criteria or instructions on which to evaluate the model output. A good evaluation criteria should provide the model with: (1) a description of the evaluation task, (2) a rubric of possible scores and their corresponding criteria, and (3) a final sentence clarifying expected score format. A good evaluation criteria should also be specific and focus on a single aspect of the model output. To evaluate a model's response on multiple criteria, use the `evaluate_llm_response_on_multiple_criteria` function and create individual criteria for each relevant evaluation task. Typical rubrics score responses either on a Likert scale from 1 to 5 or binary scale with scores of 'Yes' or 'No', depending on the specific evaluation task.
llm_promptYesThe prompt given to an LLM to generate the `llm_response` to be evaluated.
llm_responseYesThe output generated by the model in response to the `llm_prompt`, which needs to be evaluated.
expected_llm_outputNoA reference or ideal answer to compare against the `llm_response`. This is useful in cases where a specific output is expected from the model. Defaults to None.
llm_contextNoAdditional context or information provided to the model during generation. This is useful in cases where the model was provided with additional information that is not part of the `llm_prompt` or `expected_llm_output` (e.g., a RAG retrieval context). Defaults to None.
model_idNoThe Atla model ID to use for evaluation. `atla-selene` is the flagship Atla model, optimized for the highest all-round performance. `atla-selene-mini` is a compact model that is generally faster and cheaper to run. Defaults to `atla-selene`.atla-selene

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that the tool uses an Atla evaluation model under the hood and returns a dictionary. However, with no annotations provided, the description carries full burden for behavioral traits. It does not mention potential rate limits, cost implications, or authentication requirements. The description is adequate but lacks deeper operational transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with three sentences covering purpose, internal mechanism, and output format. It is front-loaded and well-structured. A minor deduction because the return type is specified in a separate block rather than integrated into the prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of 6 parameters (3 required) and the presence of an output schema (described in the return type), the description provides a complete overview. The parameter-level descriptions are very detailed, covering formatting and examples. The sibling tool is referenced, ensuring completeness around alternatives. Slightly lacking in explaining edge cases or error handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already documents all parameters thoroughly. The description does not add new meaning beyond what the schema provides; it mainly reiterates the return format. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: evaluating an LLM response using given criteria. It specifies that it uses an Atla evaluation model internally and returns a dictionary with score and critique. It also distinguishes from the sibling tool by referencing evaluate_llm_response_on_multiple_criteria in the evaluation_criteria parameter description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The evaluation_criteria parameter description explicitly instructs to use the sibling tool for multiple criteria, providing clear guidance on when to use this tool versus the alternative. Additionally, the parameter descriptions include examples and detailed instructions on crafting evaluation criteria, which serves as usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

evaluate_llm_response_on_multiple_criteriaA

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.

Returns:
    list[dict[str, str]]: A list of dictionaries containing the evaluation score
        and critique, in the format `{"score": <score>, "critique": <critique>}`.
        The order of the dictionaries in the list will match the order of the
        criteria in the `evaluation_criteria_list` argument.
ParametersJSON Schema
NameRequiredDescriptionDefault
evaluation_criteria_listYes
llm_promptYesThe prompt given to an LLM to generate the `llm_response` to be evaluated.
llm_responseYesThe output generated by the model in response to the `llm_prompt`, which needs to be evaluated.
expected_llm_outputNoA reference or ideal answer to compare against the `llm_response`. This is useful in cases where a specific output is expected from the model. Defaults to None.
llm_contextNoAdditional context or information provided to the model during generation. This is useful in cases where the model was provided with additional information that is not part of the `llm_prompt` or `expected_llm_output` (e.g., a RAG retrieval context). Defaults to None.
model_idNoThe Atla model ID to use for evaluation. `atla-selene` is the flagship Atla model, optimized for the highest all-round performance. `atla-selene-mini` is a compact model that is generally faster and cheaper to run. Defaults to `atla-selene`.atla-selene

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description adds some behavioral context (uses Atla model under the hood, returns list of dicts) but does not disclose side effects, cost, failure modes, or restrictions. It adds value beyond annotations but falls short of full transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (two sentences plus a return format note) and front-loaded with purpose. Every sentence adds value; no obvious fluff. Minor improvement possible by incorporating usage guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, output schema exists), the description provides basic purpose and return format but lacks usage guidelines, behavioral warnings, and parameter elaboration. It is incomplete for fully understanding when and how to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is high (83%), and the description does not add new meaning to individual parameters beyond the schema. It explains the return format, which aids understanding of the output but does not directly enhance parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool evaluates an LLM response across multiple criteria using an Atla model and returns a list of dictionaries with score and critique. It distinguishes from the sibling tool 'evaluate_llm_response' by emphasizing 'multiple evaluation criteria', making the purpose and differentiation explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for multiple criteria but does not explicitly state when to use this tool versus the single-criterion sibling. No when-not-to-use or alternative suggestions are provided, leaving guidance implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: one evaluates a single criterion, the other evaluates multiple criteria. Their names and descriptions make the difference unambiguous.

Naming Consistency5/5

Both tool names follow a consistent verb_noun_qualifier pattern, starting with 'evaluate_llm_response' and differentiating with '_on_multiple_criteria'. No mixing of conventions.

Tool Count3/5

With only 2 tools, the server feels thin. While the tools cover the core evaluation functionality, a typical well-scoped server has 3-15 tools, making this borderline insufficient.

Completeness3/5

The tools provide basic evaluation for single and multiple criteria, but lack supporting tools such as managing criteria, listing models, or retrieving history. The surface is minimal and may leave agents with limited options.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/atla-ai/atla-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server