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

# Plugin (MCP) reference

> How the Oqoqo MCP server works: endpoints, OAuth sign-in, approvals, web links for secrets, IDs, paging, polling, retries, and errors.

The Oqoqo MCP server lets your AI assistant create tasks and treatments, launch experiments, and read results. The [Oqoqo Plugin](https://docs.oqoqo.ai/operate/plugin.md) connects your host to it. These rules apply to every tool; [Plugin (MCP) tools](https://docs.oqoqo.ai/mcp-server/tools.md) lists each one.

Each tool matches a [CLI](https://docs.oqoqo.ai/cli/overview.md) command, with the same inputs, fields, and rules. [Ask Oqo](https://docs.oqoqo.ai/operate/ask-oqo.md) uses the same tools in the dashboard and in [Slack](https://docs.oqoqo.ai/operate/ask-oqo-in-slack.md). This server is not one of the MCP servers you add to a treatment as [tools](https://docs.oqoqo.ai/experiments/tools.md).

## Endpoints

| Server | URL | What it gives you |
| - | - | - |
| Oqoqo MCP server | `https://mcp.oqoqo.ai/mcp` | Tools that read and change your projects, with OAuth sign-in |
| Oqoqo product docs | `https://docs.oqoqo.ai/mcp` | Search over these docs |

The server keeps no session, so a host can retry any call on any connection.

## Install

[Install the Oqoqo Plugin](https://docs.oqoqo.ai/operate/plugin.md#install-the-plugin). It adds the Oqoqo MCP server, not the docs server. To add the docs server, or when your host has no plugins, see [Connect without the plugin](https://docs.oqoqo.ai/operate/plugin.md#connect-without-the-plugin).

## Sign in

The first time your host connects, it opens Oqoqo sign-in in your browser. Sign in, and choose an organization if you belong to more than one.

Where no person can sign in, such as CI or an agent's machine, [connect without the plugin](https://docs.oqoqo.ai/operate/plugin.md#connect-without-the-plugin) and set your host to send a [personal API key](https://docs.oqoqo.ai/setup/profile.md#api-keys) as the `Authorization: Bearer <key>` header. [Sign in with an API key](https://docs.oqoqo.ai/operate/plugin.md#sign-in-with-an-api-key) has the configuration for Claude Code and Codex. The key acts as you in the organization that you created it in. A key that isn't valid, or that you revoked, returns `401`.

Every tool acts as you, in the organization you signed in to, with the same access you have in the dashboard. If your sign-in names no organization and you belong to several, calls fail with `organization_ambiguous`: sign in again and choose one.

### Organization check

Every tool that changes data takes an optional `expected_organization_id`. Send the `organization.id` from `get_identity` or `get_project_context` on every write. If your sign-in has moved to another organization, the call changes nothing and returns `organization_scope_changed`.

### Projects

The server has no current project. Project-scoped tools take an optional `project_id` (`prj_`); without it, the server picks a project for that call only. To stay in one project, pass its `project_id` on every call. Tools that name a record by a unique ID, such as a `pub_` public link, need no project.

A `project_id` you can't read returns `project_not_found`, and no project at all returns `project_required`. Create one with [`manage_project`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#manage_project).

## Approvals

The server tells your host what each tool does, and your host decides how to ask you. Oqoqo never asks for a confirmation code, a typed phrase, or a second call.

| Kind | What the server sends | What happens |
| - | - | - |
| **Read-only** | `readOnlyHint: true` | Changes nothing. Hosts usually run it without asking. |
| **Changes data** | `readOnlyHint: false` | Creates or changes records. Your host's approval settings decide whether it asks. |
| **Destructive** | `destructiveHint: true` | Your host asks you first. The call acts as soon as it arrives. |
| **Destructive · Irreversible** | `destructiveHint: true` and `_meta["anthropic/requiresUserInteraction"]: true` | Can't be undone. Hosts that read this key use their strongest confirmation. |
| **You approve each call** | No extra hint | Spends runs, creates a standing rule, or makes results public. Ask Oqo asks before each call. |

The irreversible tools are [`delete_project`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#delete_project), [`delete_resources`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#delete_resources), [`delete_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#delete_schedule), and [`delete_tag`](https://docs.oqoqo.ai/mcp-server/tags-and-data#delete_tag). Claude Code in non-interactive mode (`claude -p`) refuses them.

You approve each call of [`launch_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#launch_experiment), [`rerun_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#rerun_experiment), [`test_custom_agent`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#test_custom_agent), [`manage_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#manage_schedule), [`trigger_evals`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#trigger_evals), [`trigger_insights`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#trigger_insights), [`publish_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#publish_experiment), [`update_experiment_publication`](https://docs.oqoqo.ai/mcp-server/experiments#update_experiment_publication), and [`manage_github_repository`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#manage_github_repository). Only `update_experiment_publication` is marked destructive, so in hosts other than Ask Oqo, turn on tool approval for the others to confirm each call.

### Preview before you change

When a change's effect isn't obvious, run its read-only preview, show the result to the person, then make the change.

| Preview | Then |
| - | - |
| [`preview_delete_project`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#preview_delete_project): a count of each kind of item, the running experiments it stops, and the blockers | [`delete_project`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#delete_project) |
| [`preview_delete_resources`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#preview_delete_resources): the plan, its `planHash`, and the blockers | [`delete_resources`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#delete_resources) with `plan_hash` |
| [`preview_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#preview_schedule): the next 3 launches and the runs they use | [`manage_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#manage_schedule) |
| [`preflight_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#preflight_experiment): blockers, setup links, and notices for a launch plan | [`launch_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#launch_experiment) |
| [`preview_evals`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#preview_evals) and [`preview_insights`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#preview_insights): which runs qualify and whether the models are ready | [`trigger_evals`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#trigger_evals) and [`trigger_insights`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#trigger_insights) |

## Secrets stay in the dashboard

OAuth grants, API keys, secret headers, secret values, and payments stay in the dashboard; no tool accepts them. A definition names each value it needs as `${NAME}`, never the value, and install commands can't use Variables ([Keys in a URL or an argument](https://docs.oqoqo.ai/experiments/tools.md#keys-in-a-url-or-an-argument)).

When a step needs a secure value, the tool returns the exact dashboard link, often as `setupUrl`. Open it where you're signed in, enter the value, and continue in your AI assistant. An argument that looks like a secret returns `secure_input_requires_web`, and the value is never repeated.

* [`get_setup_links`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#get_setup_links) lists each machine, MCP server, CLI, and SDK in the project that still needs a value or your account connection, with its link.
* [`inspect_mcp_account`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#inspect_mcp_account) checks your connection to an MCP server in a treatment, with the link to fix it.
* [`refresh_mcp_server_tools`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#refresh_mcp_server_tools) and [`launch_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#launch_experiment) never send saved header values to an address no person bound them to. They return `mcp_tool_check_needs_web` or the `mcp_header_values_unbound` blocker, with the link where a person selects **Refresh**.
* [`inspect_quota`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#inspect_quota) and [`list_quota_ledger`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#list_quota_ledger) return no billing link. Buy runs on **Organization settings → Usage & billing** ([Runs and billing](https://docs.oqoqo.ai/setup/billing.md)).

## IDs

Tools take and return stable public IDs whose prefix names the record's kind, such as `prj_`, `exp_`, or `run_`. Pass IDs exactly as a tool returned them, and don't build them yourself. An agent key, such as `claude-code`, names an agent with any model, and a custom agent's key starts with `acp-`. [IDs and limits](https://docs.oqoqo.ai/reference/ids-and-limits.md) lists every prefix.

## Paging

Reads return bounded pages. A `limit` above the maximum is capped, not refused. Responses are capped at 20 KiB, so a page can hold fewer items than the limit.

| Read | How to continue |
| - | - |
| Lists, such as `list_experiments` and `list_runs` | While `hasMore` is true, send `nextCursor` as `cursor`, with the same filters. |
| Byte content, such as `get_run_transcript` and `get_run_output` | Send the returned next offset as `offset` until `eof` is true. A page holds at most 12,288 bytes. |
| A run's steps in `get_run_trajectory` | While `truncated` is true, send `nextAfterOrdinal` as `after_ordinal`. |
| Version history in `inspect_resource` | While `hasMore` is true, send `nextBeforeVersion` as `beforeVersion`. |
| Ranked analysis in `analyze_results` | Never paged. When `page.truncated` is true, `page.completeData` names the full read: `query_data` or `get_run_trajectory`. |

Cursors expire after 30 minutes. An expired, changed, or foreign cursor returns `invalid_cursor`, and one whose list changed returns `stale_cursor`; either way, start again without a cursor. A row too large for a response returns `response_too_large`.

## Polling

Launches, Evals, Insights, uploads, and deletions finish after the call that starts them. Poll the matching read until it reports a final state:

* **Launches and experiments:** [`launch_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#launch_experiment), [`rerun_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#rerun_experiment), and [`test_custom_agent`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#test_custom_agent) return a `launchId` (`adm_…`) for [`get_launch_status`](https://docs.oqoqo.ai/mcp-server/experiments#get_launch_status). Once `experiment.experimentId` is set, use it with [`get_experiment_status`](https://docs.oqoqo.ai/mcp-server/experiments#get_experiment_status) and the other experiment tools.
* **Wait in the call:** while `terminal` is false, send `wait_ms` (up to 25,000) to wait for a status change, a finished run, or `terminal`, or call again after `pollAfterMs`. When `terminal` is true, read the final runs with [`list_runs`](https://docs.oqoqo.ai/mcp-server/runs-and-results#list_runs). If you call `list_runs` while a `wait_ms` status call is still waiting, `list_runs` can answer first with an older state.
* **Evals and Insights:** [`get_evals_results`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#get_evals_results) and [`get_insights_results`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#get_insights_results) also take `wait_ms`. A row is `queued` or `running` until its result is written; `completed`, `skipped`, and `failed` are final.
* **The Brief:** while `state` is `writing`, call [`get_experiment_brief`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#get_experiment_brief) again after `waitMs` milliseconds. The differences and counts are already in that read.
* **Uploads:** poll [`get_upload`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#get_upload) until `status` is `completed`, `failed`, `cancelled`, or `expired`.
* **Deletions:** poll [`get_resource_deletion`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#get_resource_deletion) until the status is final.
* **Model lists:** after `refresh_models`, poll [`inspect_project_ai`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#inspect_project_ai) until `counts.modelRefresh.refreshing` is 0. A provider's models are readable earlier, once its `modelRefresh.listedAt` is set.

### Progress counts

`get_launch_status`, `get_experiment_status`, and `get_experiment` return the same progress counts as `oqoqo experiments status`, with each run in one state:

* A queued, running, or cancelled run counts in `queued`, `running`, or `cancelled` (a blocked, then cancelled run is `cancelled`).
* A completed or errored run counts in `passed`, `failed`, `infraBlocked`, `inconclusive`, or `errored`.

`passed`, `failed`, `infraBlocked`, `inconclusive`, `cancelled`, and `errored` add up to `finished`. `infraBlocked` (and `infraBlockedCount` in `list_experiments`) counts completed or errored runs that were blocked, so Evals didn't check them.

## Retries and concurrent changes

Hosts can lose responses, so each tool that starts work takes an attempt ID you choose. Use a new ID for each change and the same ID to retry: the retry returns the first result instead of doing the work twice. Reusing an ID for a different request fails with a conflict, such as `launch_attempt_conflict` or `resource_mutation_attempt_conflict`.

| Tool | Attempt ID |
| - | - |
| `launch_experiment` | `plan.launchAttemptId` |
| `rerun_experiment`, `test_custom_agent`, `get_experiment_plan` | `launch_attempt_id` |
| `manage_project` (create) | `mutation_attempt_id` |
| `author_resource`, `bulk_author_resources`, `manage_resource` | `mutationAttemptId` on each operation |
| `manage_schedule` (create and update), `delete_resources`, `publish_experiment`, `update_experiment_publication` | `attempt_id` |
| `trigger_evals`, `trigger_insights` | `trigger_attempt_id` |
| `complete_upload` | `upload_id` |

So that two people or AI assistants can't overwrite each other, a change also sends the version you read. If the record changed since, nothing changes and the call returns an error: read again and retry.

| Field you send | Read it from | Stale result |
| - | - | - |
| `lock_version` (schedules, public links) | `get_schedule`, `get_experiment_publication` | `schedule_changed`, `publication_changed` |
| `expected_updated_at` (tags, projects) | `list_tags`, `get_project_context` | `tag_changed`, `project_update_stale` |
| `expectedUpdatedAt` (catalog records) | `inspect_catalog` with `projection: "full"` | `resource_revision_conflict` |
| `expectedRevision` and the other revisions (agents, models, Oqoqo AI defaults) | `inspect_project_ai` | `configuration_changed`, `project_ai_configuration_changed` |
| `projectConfigurationRevision`, `organizationConfigurationRevision` (launch plans) | `inspect_catalog` agent items, or `preflight_experiment` | `configuration_changed` |
| `plan_hash` (resource deletion) | `preview_delete_resources` | `resource_deletion_plan_changed` |

## Errors

A failed call returns an MCP tool error (`isError: true`). Its text is one JSON object:

```json theme={null}
{
  "error": {
    "code": "schedule_changed",
    "message": "This schedule changed after you read it (lock version is now 4). Read it again, then retry.",
    "details": { "lockVersion": 4 }
  }
}
```

`code` is stable, so your AI assistant or script can branch on it. `message` says what to do next. `details` appears only when it adds facts, such as a `setupUrl` or the current revision. Arguments that don't match a tool's schema fail before the tool runs, with a message that lists the fields the tool accepts.

| Code | Meaning |
| - | - |
| `organization_ambiguous` | Your sign-in names no organization and you belong to several. Sign in again and choose one. |
| `organization_required` | Your sign-in has no organization. |
| `organization_scope_changed` | `expected_organization_id` does not match your sign-in. Nothing changed. |
| `forbidden` | Your organization does not have access. |
| `project_not_found`, `project_required` | The project does not exist for you, or no project could be found. |
| `secure_input_requires_web` | An argument looked like a secret. Enter it on the web link instead. |
| `mcp_tool_check_needs_web` | The MCP server version's saved values are not bound to its address. A person opens `setupUrl` and selects **Refresh**. |
| `mcp_header_values_unbound` | A launch or preflight blocker: an MCP server version would send saved values to an unbound address. Give the person `setupUrl` (the version's **Tools** tab) to check the address and select **Refresh**, and don't launch until they do. |
| `invalid_cursor`, `stale_cursor` | Read the first page again without a cursor. |
| `response_too_large` | One row or the fixed fields cannot fit a response. Narrow the read. |
| `rate_limited` | Too many calls. Wait and retry. |
| `upstream_error` | A service that Oqoqo depends on did not answer. Retry. |
| `internal_error` | The request could not be completed. |

Tool-specific codes, such as `schedule_limit_reached`, appear under each tool on its area page below (see [Plugin (MCP) tools](https://docs.oqoqo.ai/mcp-server/tools.md) for the full index).

## Tools by area

The server has 83 tools, organized into 10 area pages that match the [CLI reference](https://docs.oqoqo.ai/cli/overview.md). See [Plugin (MCP) tools](https://docs.oqoqo.ai/mcp-server/tools.md) for a single-table index.

| Area | Tools |
| - | - |
| [Identity and projects](https://docs.oqoqo.ai/mcp-server/identity-and-projects.md) | [`get_identity`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#get_identity), [`get_project_context`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#get_project_context), [`manage_project`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#manage_project), [`preview_delete_project`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#preview_delete_project), [`delete_project`](https://docs.oqoqo.ai/mcp-server/identity-and-projects#delete_project) |
| [Catalog, resources, and uploads](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads.md) | [`inspect_catalog`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#inspect_catalog), [`browse_github_source`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#browse_github_source), [`inspect_resource`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#inspect_resource), [`inspect_resource_impact`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#inspect_resource_impact), [`author_resource`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#author_resource), [`bulk_author_resources`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#bulk_author_resources), [`manage_resource`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#manage_resource), [`download_resource_archive`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#download_resource_archive), [`create_upload`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#create_upload), [`get_upload`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#get_upload), [`complete_upload`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#complete_upload), [`cancel_upload`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#cancel_upload), [`preview_delete_resources`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#preview_delete_resources), [`delete_resources`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#delete_resources), [`get_resource_deletion`](https://docs.oqoqo.ai/mcp-server/catalog-and-uploads#get_resource_deletion) |
| [Experiments](https://docs.oqoqo.ai/mcp-server/experiments.md) | [`preflight_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#preflight_experiment), [`launch_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#launch_experiment), [`get_launch_status`](https://docs.oqoqo.ai/mcp-server/experiments#get_launch_status), [`list_experiments`](https://docs.oqoqo.ai/mcp-server/experiments#list_experiments), [`get_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#get_experiment), [`rename_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#rename_experiment), [`get_experiment_plan`](https://docs.oqoqo.ai/mcp-server/experiments#get_experiment_plan), [`rerun_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#rerun_experiment), [`get_experiment_status`](https://docs.oqoqo.ai/mcp-server/experiments#get_experiment_status), [`cancel_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#cancel_experiment), [`publish_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#publish_experiment), [`list_experiment_publications`](https://docs.oqoqo.ai/mcp-server/experiments#list_experiment_publications), [`get_experiment_publication`](https://docs.oqoqo.ai/mcp-server/experiments#get_experiment_publication), [`update_experiment_publication`](https://docs.oqoqo.ai/mcp-server/experiments#update_experiment_publication), [`unpublish_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#unpublish_experiment), [`get_public_experiment`](https://docs.oqoqo.ai/mcp-server/experiments#get_public_experiment) |
| [Schedules](https://docs.oqoqo.ai/mcp-server/schedules.md) | [`list_schedules`](https://docs.oqoqo.ai/mcp-server/schedules#list_schedules), [`get_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#get_schedule), [`preview_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#preview_schedule), [`manage_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#manage_schedule), [`delete_schedule`](https://docs.oqoqo.ai/mcp-server/schedules#delete_schedule) |
| [Runs and results](https://docs.oqoqo.ai/mcp-server/runs-and-results.md) | [`list_runs`](https://docs.oqoqo.ai/mcp-server/runs-and-results#list_runs), [`get_run_profile`](https://docs.oqoqo.ai/mcp-server/runs-and-results#get_run_profile), [`get_run_trajectory`](https://docs.oqoqo.ai/mcp-server/runs-and-results#get_run_trajectory), [`get_run_transcript`](https://docs.oqoqo.ai/mcp-server/runs-and-results#get_run_transcript), [`get_run_output`](https://docs.oqoqo.ai/mcp-server/runs-and-results#get_run_output), [`analyze_results`](https://docs.oqoqo.ai/mcp-server/runs-and-results#analyze_results) |
| [Frictions](https://docs.oqoqo.ai/mcp-server/frictions.md) | [`list_frictions`](https://docs.oqoqo.ai/mcp-server/frictions#list_frictions), [`get_friction`](https://docs.oqoqo.ai/mcp-server/frictions#get_friction) |
| [Evals & Insights tools](https://docs.oqoqo.ai/mcp-server/evals-and-insights.md) | [`preview_evals`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#preview_evals), [`trigger_evals`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#trigger_evals), [`list_evals`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#list_evals), [`get_evals_results`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#get_evals_results), [`get_evals_comparisons`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#get_evals_comparisons), [`get_experiment_brief`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#get_experiment_brief), [`preview_insights`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#preview_insights), [`trigger_insights`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#trigger_insights), [`list_insights`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#list_insights), [`get_insights_results`](https://docs.oqoqo.ai/mcp-server/evals-and-insights#get_insights_results) |
| [Tags & data queries](https://docs.oqoqo.ai/mcp-server/tags-and-data.md) | [`list_tags`](https://docs.oqoqo.ai/mcp-server/tags-and-data#list_tags), [`update_tags`](https://docs.oqoqo.ai/mcp-server/tags-and-data#update_tags), [`rename_tag`](https://docs.oqoqo.ai/mcp-server/tags-and-data#rename_tag), [`delete_tag`](https://docs.oqoqo.ai/mcp-server/tags-and-data#delete_tag), [`inspect_data_model`](https://docs.oqoqo.ai/mcp-server/tags-and-data#inspect_data_model), [`query_data`](https://docs.oqoqo.ai/mcp-server/tags-and-data#query_data) |
| [Agents, models, and setup](https://docs.oqoqo.ai/mcp-server/agents-and-setup.md) | [`inspect_project_ai`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#inspect_project_ai), [`manage_project_ai`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#manage_project_ai), [`delete_project_ai`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#delete_project_ai), [`test_custom_agent`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#test_custom_agent), [`get_setup_links`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#get_setup_links), [`inspect_mcp_account`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#inspect_mcp_account), [`detect_mcp_auth_mode`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#detect_mcp_auth_mode), [`list_mcp_server_tools`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#list_mcp_server_tools), [`refresh_mcp_server_tools`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#refresh_mcp_server_tools), [`list_github_repositories`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#list_github_repositories), [`manage_github_repository`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#manage_github_repository), [`disconnect_github_account`](https://docs.oqoqo.ai/mcp-server/agents-and-setup#disconnect_github_account) |
| [Quota and notifications](https://docs.oqoqo.ai/mcp-server/quota-and-notifications.md) | [`inspect_quota`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#inspect_quota), [`list_quota_ledger`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#list_quota_ledger), [`list_notifications`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#list_notifications), [`acknowledge_notifications`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#acknowledge_notifications), [`inspect_notification_preferences`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#inspect_notification_preferences), [`manage_notification_preferences`](https://docs.oqoqo.ai/mcp-server/quota-and-notifications#manage_notification_preferences) |

## Related

> [card] [Plugin (MCP) tools](https://docs.oqoqo.ai/mcp-server/tools.md)
>
> Index of all 83 tools by area and matching CLI commands.

> [card] [Plugin (MCP) skills](https://docs.oqoqo.ai/mcp-server/skills.md)
>
> The four skills, what they do, and the tools they call.

> [card] [Install the Oqoqo Plugin](https://docs.oqoqo.ai/operate/plugin.md)
>
> Install the plugin in your host and sign in.

> [card] [CLI reference](https://docs.oqoqo.ai/cli/overview.md)
>
> The same operations from your terminal and scripts.

> [card] [IDs and limits](https://docs.oqoqo.ai/reference/ids-and-limits.md)
>
> Every ID prefix and product limit.


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