# extract_project_server_summaries

> **Function** in `deepagents_code`

📖 [View in docs](https://reference.langchain.com/python/deepagents-code/mcp_tools/extract_project_server_summaries)

Return `(name, kind, summary)` for every server in a project config.

Used by the trust prompt and the untrusted-config skip warning so that
both stdio servers (which spawn local commands) and remote servers
(which can SSRF or exfiltrate environment variables via interpolated
headers when an attacker controls `.mcp.json`) are gated identically.

## Signature

```python
extract_project_server_summaries(
    config: dict[str, Any],
) -> list[tuple[str, str, str]]
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `config` | `dict[str, Any]` | Yes | Parsed MCP config dictionary. |

## Returns

`list[tuple[str, str, str]]`

List of `(server_name, kind, summary)`. `kind` is `"stdio"`,
`"http"`, `"sse"`, or `"unknown"`. `summary` is `"<command> <args>"`
for stdio entries and the URL for remote entries.

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/d1c6946218b4f0f86ab7b02b6bb6af1e4b75cede/libs/code/deepagents_code/mcp_tools.py#L791)