Multi-Turn MCP-Use

The Multi-Turn MCP Use metric is a conversational metric that uses LLM-as-a-judge to evaluate how effectively an MCP based LLM agent makes use of the mcp servers it has access to. It evaluates the MCP primitives called as well as the arguments generated by the LLM app.

Required Arguments

To use the MultiTurnMCPUseMetric, you'll have to provide the following arguments when creating a ConversationalTestCase:

• turns
• mcp_servers

You will also need to provide mcp_tools_called, mcp_resources_called and mcp_prompts_called inside the turns whenever there is an MCP interaction in your agent's workflow. You can learn more about creating MCP test cases here.

You can learn more about how it is calculated here.

Usage

First, set the eval mode:

deepeval set-eval-mode llm         # LLM-as-a-judge (default)
deepeval set-eval-mode hybrid      # LLM extracts, Jev decides
deepeval set-eval-mode system_one  # Jev-as-a-judge, no LLM

The MultiTurnMCPUseMetric() can be used for end-to-end multi-turn evaluations of MCP based agents.

from deepeval.test_case import Turn, ConversationalTestCase, MCPServer
from deepeval.metrics import MultiTurnMCPUseMetric
from deepeval import evaluate

convo_test_case = ConversationalTestCase(
    turns=[Turn(role="...", content="..."), Turn(role="...", content="...")],
    mcp_servers=[MCPServer(...)]
)
metric = MultiTurnMCPUseMetric(threshold=0.5)

# To run metric as a standalone
# metric.measure(convo_test_case)
# print(metric.score, metric.reason)

evaluate(test_cases=[convo_test_case], metrics=[metric])

There are NINE optional parameters when creating a MultiTurnMCPUseMetric:

• [Optional] threshold: a number representing the minimum passing threshold. Can also be set to None to run the metric in score-only mode. Defaulted to 0.5.
• [Optional] model: a string specifying which of OpenAI's GPT models to use, OR any custom LLM model of type DeepEvalBaseLLM. Defaulted to gpt-5.4.
• [Optional] include_reason: a boolean which when set to True, will include a reason for its evaluation score. Defaulted to True.
• [Optional] strict_mode: a boolean which when set to True, enforces a binary metric score: 1 for perfection, 0 otherwise. It also overrides the current threshold and sets it to 1. Defaulted to False.

• [Optional] async_mode: a boolean which when set to True, enables concurrent execution within the measure() method. Defaulted to True.

• [Optional] verbose_mode: a boolean which when set to True, prints the intermediate steps used to calculate said metric to the console, as outlined in the How Is It Calculated section. Defaulted to False.
• [Optional] flaky: a boolean which when set to True, marks the metric as flaky. Defaulted to False.
• [Optional] system_one_model: the Jev model to use, as a string or a DeepEvalBaseSystemOneModel. Only used under hybrid or system_one eval_mode. Defaulted to jev-latest.
• [Optional] eval_mode: llm, hybrid or system_one, choosing whether an LLM, Jev, or both judge. Defaulted to the configured eval mode (llm unless set).

As a standalone

You can also run the MultiTurnMCPUseMetric on a single test case as a standalone, one-off execution.

...

metric.measure(convo_test_case)
print(metric.score, metric.reason)

How Is It Calculated

You can change how the MultiTurnMCPUseMetric is calculated by setting the eval mode.

LLM-as-a-judge

The MultiTurnMCPUseMetric score is calculated according to the following equation:

• The AlignmentScore is judged by an evaluation model based on which primitives were called and their generated arguments with respect to the task.
• MCP Interactions are the number of times the LLM app uses the MCP server's capabilities.

Hybrid

Under the hybrid eval mode, the LLM still splits the conversation into tasks, but each task's primitive usage and argument correctness scores are rated by Jev, a System One model, on a scale mapped onto 0 to 1. The equation and the LLM-written final reason are unchanged. If a Jev call fails, the LLM makes that decision instead.

Jev-as-a-judge

Under the system_one eval mode, Jev judges the whole metric in one request. It is sent the whole conversation (with the MCP calls in each turn) and the available mcp_servers and asked three questions:

Each answer becomes a value in $[0, 1]$ and the score is their weighted mean. No LLM is called: the reason lists each answer with its probability, and metric.confidence reports how decisive Jev was.

FAQs