> ## Documentation Index
> Fetch the complete documentation index at: https://dev-docs.altrum.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP tools

> Register your organization's MCP servers in Altrum, control which tools each AI system and key can use, and use them from coding agents and applications.

<Info>This is in development. Details may change before it is available.</Info>

MCP servers give models tools: search a ticket system, read a repository, query a database. Register them once in Altrum, and every tool call goes through the same governance as model requests: access rules, guardrails and logs.

## Register an MCP server

Owners and admins open **AI Gateway**, then **MCP servers**, and add a remote server by its URL (HTTP or SSE). Choose how Altrum authenticates to it:

| Authentication | Who connects |
| - | - |
| None | Nobody: the server is open. |
| Shared headers | An admin enters headers, such as an API key, once for the organization. |
| Shared OAuth | An admin signs in once, and the organization uses that connection. |
| Per person, OAuth | Each person signs in with their own account, such as their own GitHub. |
| Per person, headers | Each person enters their own key for the server. |

Servers that run as local processes are not supported. Altrum refuses addresses on private networks, and checks the address again every time it connects, so a name that later points somewhere private is refused too. Code mode, running tools without your application asking, and skipping the server's certificate check are not offered.

## Connect your own account

For servers that act as each person, open **AI Gateway**, then **MCP servers**, and connect your account. Tool calls made with your [personal key](/ai-gateway/virtual-keys#personal-keys) then run as you. A request made with an organization or AI system key cannot use a per-person server.

## Choose who can use which tools

Owners and admins choose which servers and tools are allowed for the organization's keys, for each AI system, and for each key. A key sees only the tools it is allowed. A list set on an AI system limits every key of that AI system, and a list set on the organization limits the organization's own keys. A server that is not named in a list is not reachable, and `*` stands for every tool of a server.

## Use the tools

<Tabs>
  <Tab title="Coding agents">
    Add Altrum's MCP endpoint, `https://api.altrum.ai/mcp`, to your coding agent with your personal key. The agent sees the tools your key allows, across all your organization's servers. See [Coding agents](/ai-gateway/coding-agents).
  </Tab>

  <Tab title="Your applications">
    Altrum adds the allowed tools to your chat requests. When the model asks for a tool, your application asks Altrum to run it and sends the result back to the model.
  </Tab>
</Tabs>

## When a tool cannot run

A server that works with each person's own account needs a personal key. Two answers explain what is missing, word for word:

* `<server> needs a personal key: it works with each person's own account, which a shared key does not have. Use a personal key to call it.` The tool is also left out of the list an organization or AI system key sees.
* `Your account is not connected to <server>. Connect it in Altrum under AI Gateway, MCP, then try again.`

## Governance on every call

* Tool arguments are checked by your guardrails before the tool runs, and results before they return to the model. See [Guardrails at runtime](/guardrails/at-runtime#tool-calls).
* Every call is logged: the tool, the server, who called it, how long it took and whether it worked. Arguments and results are kept only when content logging is on. See [Request logs](/ai-gateway/request-logs).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.