Skip to main content

Documentation Index

Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Why

  • An MCP server tool call may return a large amount of data, which can quickly fill the available context window.
  • The agent may not be able to control how much data an MCP server returns in a tool response by modifying the tool arguments alone. For example, fetching a single pull request can still return a very large description field.

​
How it works

​
Configuration

Work in progress

​
Example

User

Can you please list the mcp servers I have access to

Assistant

Let me get more information about the user.
Tool Call
{}
Tool Response
{
  "id": "cm1fa35mt009e0trd11v5831p",
  "subjectSlug": "john@example.com",
  ...
}

Assistant

Let me list the MCP servers you have access to.
Tool response blocked — list_mcp_servers returned too much data. The full result was not sent to the model; it was saved to disk and only a preview was returned.

list_mcp_servers

Tool Call
{
  createdBySubjectSlug: "john@example.com",
}
Tool Response (blocked) — Full result saved to /tmp/tool-id-xyz-output
Use sandbox to read parts of the file or extract data.
Use sandbox-schema-infer to understand the schema

Preview (first and last 100 chars):
{"data":[{"id":"v3sgnimki67gd1do5vkcv9wz","name":"test-realtime-global","fqn":"truefoundry:google-ve ... 51.458Z","updatedAt":"2026-05-19T13:23:46.269Z","createdBy":"john@truefoundry.com"}],"total":180}

Assistant

Let me get a preview of the data and print the schema.

sandbox

Tool Call
head -c 200 /tmp/tool-id-xyz-output && echo \"==\" && genson /tmp/tool-id-xyz-output
Tool Response
{"$schema":"http://json-schema.org/schema#","type":"object","properties":{"data":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"name":{"type":"string"},"createdBySubject":{"type":"object","properties":{"subjectSlug":{"type":"string"}},"required":["subjectSlug"]}},"required":["id","name","createdBySubject"]}},"total":{"type":"integer"}},"required":["data","total"]}

Assistant

Now I understand the schema of the MCP servers output file. Let me write code to parse the MCP server names.
Tool Call
cat << 'EOF' > /tmp/parse_mcp_servers.py
import json
with open('/tmp/tool-id-xyz-output', 'r') as f:
    data = json.load(f)
    for item in data['data']:
        print(item['name'])
EOF
python3 /tmp/parse_mcp_servers.py
Tool Response
test-realtime-global
slack-mcp
google-calendar-mcp
...

Assistant

Hey John, here are the MCP servers you have access to:
  • test-realtime-global
  • slack-mcp
  • google-calendar-mcp
  • …