---
title: "Live tool list from an MCP server"
method: GET
path: "/voice/mcp-servers/{mcp_server_id}/tools"
tags: ["Voice"]
---

# Live tool list from an MCP server

`GET /voice/mcp-servers/{mcp_server_id}/tools`

## Request

- Base URL: `https://be.graph8.com/api/v1`
- URL: `https://be.graph8.com/api/v1/voice/mcp-servers/{mcp_server_id}/tools`
- Auth: HTTP bearer

Ask the MCP server itself what tools it offers.

THIS REACHES OUTSIDE GRAPH8. The server is one the customer configured, and
the connection is made by our infrastructure on their behalf - the same
reasoning that put `POST /skills/{action_id}/execute` in the `external`
tier. It is an explicit rule in `build_scope_policy.py::classify`, because
a GET otherwise derives `read` unconditionally and this one is not free of
side effects: it can hang on an unreachable server, and `refresh=true`
overwrites the cache the route beside it serves.

Use `/tools/cached` for anything routine.

## Path parameters

- `mcp_server_id` string, required: MCP server id.

## Query parameters

- `refresh` boolean: True re-reads from the server and replaces the cache.

## Headers

- `Authorization` string, nullable
- `X-Target-Org-Id` string, nullable

## Response `200`

Successful Response

- ApiResponseVoiceListPayload
  - `data` VoiceListPayload, required: A LIST result from voice, normalised so `items` is always present. Voice is inconsistent about whether a list comes back bare or under a named key (`collections`, `files`, `routes`, `chats`, ...). Both are preserved: the original key is kept for anyone reading voice's docs, and `items` always holds the same rows so a client can page one way.
    - `items` unknown[]
      - unknown
  - `pagination` PaginationMeta
    - `page` integer, required: Current page number (1-indexed)
    - `limit` integer, required: Items per page
    - `total` integer, required: Total number of items
    - `has_next` boolean, required: Whether there are more pages
    - `next_cursor` string, nullable: Opaque cursor for the next page; null when there are no more items. Pass it back as the `cursor` query param to fetch the following page without computing page numbers.
    - `total_available` integer, nullable: Search endpoints only: how many records really match, when known. Can be larger than `total`, which is capped at the 10,000 results that can be paged. For company search this is a distinct-company estimate. Null when unknown; absent outside search.
    - `total_is_lower_bound` boolean, nullable: Search endpoints only: true when more records match than `total` shows (the result set is larger than the 10,000 results that can be paged). Absent outside search.
    - `notes` string[], nullable: Search endpoints only: plain-language notes about the result, e.g. that more records match than can be paged, or that a reversed `between` range was put in order.

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/graph8/apis/graph8-developer-api.md) · [All operations](https://skmtc.dev/graph8/apis/graph8-developer-api/llms.txt) · [OpenAPI document](https://skmtc.dev/graph8/apis/graph8-developer-api/revisions/2e7cfa0ca921?raw)