# EXTREMELY agency (npm · @extremely-agency/mcp)

Your agency of AI agents in your AI app: what agents did, approvals, requests, jobs and reports.

- Trust score: 78/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `@extremely-agency/mcp`: 78/100 (this document), [markdown](https://verifymcp.io/servers/agency-extremely-agency/extremely-agency-mcp.md), [page](https://verifymcp.io/servers/agency-extremely-agency/extremely-agency-mcp)

## Channel facts

- Registry: `npm`
- Package: `@extremely-agency/mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to maxkxd/extremely-autonomous-agents).
  - Clear OSI-approved license (AGPL-3.0-only).
  - Actively maintained (last published 15 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5005 tokens (~161/item across 31 items; 31 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the EXTREMELY agency MCP server?

EXTREMELY agency runs locally as an npm package, launched with npx -y @extremely-agency/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add agency-extremely-agency -- npx -y @extremely-agency/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "agency-extremely-agency": {
      "command": "npx",
      "args": [
        "-y",
        "@extremely-agency/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "agency-extremely-agency": {
      "command": "npx",
      "args": [
        "-y",
        "@extremely-agency/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add agency-extremely-agency -- npx -y @extremely-agency/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agency-extremely-agency": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@extremely-agency/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agency-extremely-agency --command npx --arg -y --arg @extremely-agency/mcp
```

### Hermes

```yaml
mcp_servers:
  agency-extremely-agency:
    command: "npx"
    args: ["-y", "@extremely-agency/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "agency-extremely-agency": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@extremely-agency/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add agency-extremely-agency -t stdio -c npx -a -y @extremely-agency/mcp
```

### Other

```json
{
  "mcpServers": {
    "agency-extremely-agency": {
      "command": "npx",
      "args": [
        "-y",
        "@extremely-agency/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-06 (score 78, +20)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Source repository: unverified → pass

### 2026-11-05 (score 58)

First indexed and scored.

## MCP tools (31)

### `list_agencies` (~42 tokens)

List your agencies

Your own agency and every organization you are in, with your role in each and whether it answers right now. Pass one as `agency` to any other tool.

### `list_requests` (~83 tokens)

List requests

Requests agents filed for things they can't do themselves: what they need, why, where each stands, and the conversation with the Agency Engineer.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `include_closed` (boolean): Closed ones too (default: open only)

### `answer_request` (~105 tokens)

Close a request

Close a request: done (say what was done, so the agent knows) or rejected (anything drafted for it is discarded). The agent hears on its next run.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `answer` (string): What was done, or why not
- `request_id` (number, required): The request number
- `status` (string, required)

### `reply_to_request` (~93 tokens)

Reply on a request

Write in an open request, to the Agency Engineer (as in the app: everyone on the request sees it, and the Engineer is woken to answer).

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `request_id` (number, required): The request number
- `text` (string, required): What to say

### `give_task` (~116 tokens)

Give an agent a job

Give an agent a job, from you: it starts on it as soon as it can and marks it done with the result (agent_activity shows it). For a question or a quick word, run_agent with a message instead.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id (list_agents)
- `task` (string, required): The whole job, with everything it needs to know

### `list_agents` (~73 tokens)

List agents

Every agent: id, name, department, owner, state (active / draining = standby / stopped), ferocity level, models, and whether it is built in.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.

### `read_agent` (~80 tokens)

Read an agent

An agent's files (CHARTER.md, TOOLS.yaml, KPI.yaml), its models and state, its last runs and its memory notes.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id

### `write_agent_file` (~120 tokens)

Replace an agent's file

Replace one of an agent's files: CHARTER.md (its job), TOOLS.yaml (tools, tiers, approval windows, ferocity plan) or KPI.yaml (which actions count as output). read_agent first. Its next run uses it.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id
- `content` (string, required): The whole new file
- `file` (string, required)

### `list_models` (~57 tokens)

List AI models

The AI models connected in the app, which agents can be given (set_agent_models).

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.

### `set_agent_models` (~100 tokens)

Set an agent's models

An agent's models: up to three, in order of preference; it falls to the next when one fails. Each {connection, model, effort: low|medium|high|max}, from list_models.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id
- `models` (array, required)

### `set_agent` (~114 tokens)

Set an agent's ferocity or state

An agent's ferocity (how hard it works: Chill, Steady, Driven, Relentless, Apocalyptic) or state (active, draining = standby: starts nothing itself, stopped: runs nothing). Built-in agents have neither.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id
- `ferocity` (string)
- `state` (string)

### `builder_guide` (~113 tokens)

Agent builder guide

Read this first when making an agent: the agent builder's whole brief - how agents work here, the tool catalogue and default tiers, the tools every agent gets, this organization and the person, the fleet, connected services and their tools and events, the connected models, how to interview the person, and how to tier. create_agent's fields carry the rest.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.

### `check_build` (~993 tokens)

Check an agent build

Check a build before creating it, without creating anything: the same input as create_agent. Answers with what's wrong, or what it would make.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `approval_hours` (array, required): One entry per T2 tool
- `charter` (string, required): The full CHARTER.md in Markdown, written for this organization: # CHARTER - <name>, then ## Mission, ## What this agent does, ## What this agent does not do, ## Autonomy tier (which actions are T0, T…
- `department` (string, required)
- `events` (array, required): What wakes this agent besides its schedule: things happening at a service that it reacts to - a new error report, a support ticket, an alarm, a payment failing. Empty for an agent that only works on…
- `ferocity` (object, required): How hard it works at each ferocity level, set for this job. The person picks the level on the card.
- `kpi` (array, required): 1-4 actions whose successful calls are the real output of this agent. Never reads or plumbing.
- `max_runs_per_day` (number, required): Runaway backstop, not the cadence: comfortably above what the job needs
- `models` (array, required): Up to three models in order of preference, from "Models connected" only: the first is used, the others take over if it fails. Pick the best fit for the job - strong models for open-ended judgement, f…
- `name` (string, required): Short agent name, 1-3 words, title case, e.g. "Invoice Chaser"
- `natural_limits` (array, required): Caps on an action at every ferocity - ONLY ones the person asked for in this conversation, in their own words ("at most one post a day"). Never add one because it seems sensible: the agency is here f…
- `new_events` (array, required): Events nothing connected provides yet that this agent should wake on. The Agency Engineer sets each up and the person connects it. Empty when none.
- `new_tools` (array, required): Tools that neither the fleet nor the catalogue has and this agent needs. Empty when existing tools cover it.
- `person_notes` (array, required): New facts about the person you're talking to. Only what will still be true and useful to an agent months from now: lasting roles, responsibilities, preferences, standards and how they like to work. N…
- `profile_notes` (array, required): New facts about the organization that every agent should know. Only what will still be true and useful to an agent months from now: lasting roles, responsibilities, preferences, standards and how the…
- `report_place` (string): Where this agent's reports go when the person named a place in this conversation: exactly where (a folder's full path, "email to the owner", the Drive folder or Notion page), then " | " and the tool…
- `tools` (array, required): Every tool the job needs. Leave out anything it does not need. Do not list the fleet plumbing.

### `create_agent` (~1055 tokens)

Create an agent

Add a new agent, as the app's agent builder would (read builder_guide first, and talk to the person the way it says): the full build - name, department, Charter, tools with tiers, events, KPIs, models, ferocity plan. Every id must exist (the guide lists them) or be one of its own new_tools / new_events, which go to the Agency Engineer as requests. Answers with what it made.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `approval_hours` (array, required): One entry per T2 tool
- `charter` (string, required): The full CHARTER.md in Markdown, written for this organization: # CHARTER - <name>, then ## Mission, ## What this agent does, ## What this agent does not do, ## Autonomy tier (which actions are T0, T…
- `department` (string, required)
- `events` (array, required): What wakes this agent besides its schedule: things happening at a service that it reacts to - a new error report, a support ticket, an alarm, a payment failing. Empty for an agent that only works on…
- `ferocity` (object, required): How hard it works at each ferocity level, set for this job. The person picks the level on the card.
- `kpi` (array, required): 1-4 actions whose successful calls are the real output of this agent. Never reads or plumbing.
- `max_runs_per_day` (number, required): Runaway backstop, not the cadence: comfortably above what the job needs
- `models` (array, required): Up to three models in order of preference, from "Models connected" only: the first is used, the others take over if it fails. Pick the best fit for the job - strong models for open-ended judgement, f…
- `name` (string, required): Short agent name, 1-3 words, title case, e.g. "Invoice Chaser"
- `natural_limits` (array, required): Caps on an action at every ferocity - ONLY ones the person asked for in this conversation, in their own words ("at most one post a day"). Never add one because it seems sensible: the agency is here f…
- `new_events` (array, required): Events nothing connected provides yet that this agent should wake on. The Agency Engineer sets each up and the person connects it. Empty when none.
- `new_tools` (array, required): Tools that neither the fleet nor the catalogue has and this agent needs. Empty when existing tools cover it.
- `person_notes` (array, required): New facts about the person you're talking to. Only what will still be true and useful to an agent months from now: lasting roles, responsibilities, preferences, standards and how they like to work. N…
- `profile_notes` (array, required): New facts about the organization that every agent should know. Only what will still be true and useful to an agent months from now: lasting roles, responsibilities, preferences, standards and how the…
- `report_place` (string): Where this agent's reports go when the person named a place in this conversation: exactly where (a folder's full path, "email to the owner", the Drive folder or Notion page), then " | " and the tool…
- `tools` (array, required): Every tool the job needs. Leave out anything it does not need. Do not list the fleet plumbing.

### `delete_agent` (~89 tokens)

Delete an agent

Delete an agent: its files go, its approvals and requests are closed, work handed to it is closed as not done. Its past runs stay in Usage. Built-in agents can't be deleted.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id

### `run_agent` (~99 tokens)

Run or message an agent

Start an agent now. With a message, it answers it in its DM channel (as if the person wrote it); without, it does its job as on Run now.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id
- `message` (string): Optional: what to say to it

### `list_approvals` (~77 tokens)

List approvals

Agents' actions waiting on a person in the app (sending, posting, going live...): only the ones that are yours to decide. decide_approval approves or rejects one.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.

### `decide_approval` (~123 tokens)

Approve or reject an action

Approve or reject one of the actions in list_approvals, as on the Approvals screen: approved, it runs now and the agent hears the result; rejected, the agent is told (with the note, if any).

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `approval_id` (string, required): The id from list_approvals
- `decision` (string, required)
- `note` (string): Optional: why, for the agent

### `agency_today` (~122 tokens)

What the agency did today

What the whole agency did since a time (default: the start of today, the agency's own clock): per agent its runs, output actions and last summary, plus what's waiting on a person (approvals, open requests).

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `since` (string): Optional: an ISO date or time, e.g. 2026-11-05 or 2026-11-05T09:00

### `agent_activity` (~132 tokens)

What an agent did

What one agent did since a time (default: the start of today): its DM channel posts (each run's write-up and the tools it used), the people's messages to it, and the jobs given to it.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id (list_agents)
- `limit` (number): Optional: at most this many posts, newest kept (default 30)
- `since` (string): Optional: an ISO date or time

### `latest_report` (~89 tokens)

An agent's latest report

An agent's latest report: the write-up of its last run that made one, and where its reports go (the place its person chose, e.g. a Drive folder).

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id (list_agents)

### `list_integrations` (~69 tokens)

List integrations

Every integration (the services agents' tools run on): connected or not, draft or live, its tools. Plus whether code plugins are allowed.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.

### `read_integration` (~85 tokens)

Read an integration

An integration's definition (YAML), and a plugin's code. The shipped ones - brave-search (HTTP), github and gmail (code) - show the format.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `integration_id` (string, required): The integration id

### `write_integration` (~122 tokens)

Write an integration draft

Save an integration definition (YAML, kind http | mcp | code) as a draft: it shows in the app's Settings > Connectors to be connected, and no agent can call it until publish_integration. Redrafting a live one keeps the live one working meanwhile. Keys and sign-ins are added by the person in Settings, never here.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `yaml` (string, required): The whole definition

### `write_plugin` (~135 tokens)

Write a code plugin

Save a code plugin's TypeScript (only if code plugins are allowed in Settings): export default { tools: [{ id, tier, description, input, run: async (args, token, kit) => string }] }. Network only through kit.fetch; it runs sandboxed with the permissions its kind: code definition declares. It runs only once published.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `code` (string, required): The whole TypeScript file
- `module` (string, required): The module name its definition names

### `test_integration` (~105 tokens)

Try an integration tool

Call one of an integration's tools for real (a draft or a live one), and see what an agent would. A plugin's code can't be tried before it's published.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `args` (object): Its input
- `integration_id` (string, required): The integration id
- `tool` (string, required): The tool id

### `publish_integration` (~159 tokens)

Publish an integration

Make a draft live, and optionally give its tools to an agent. A plugin first gets the independent security review; a serious finding stops it. Done here, it doesn't wait for the app's Approvals.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `events` (array): For for_agent: its events the agent should wake on
- `for_agent` (string): Optional: the agent that gets its tools
- `integration_id` (string, required): The draft
- `tools` (array): For for_agent: the tools to give and their tiers (T0 read, T1 reversible write, T2 needs a person)

### `test_event` (~95 tokens)

Try an event

Try an integration's event (draft or live) without waking anyone: a real poll showing what it finds, and the webhook address to paste into the service.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `event_id` (string, required): The event (server.event)
- `integration_id` (string, required): The integration id

### `give_events` (~91 tokens)

Subscribe an agent to events

Subscribe an agent to live events: it wakes when they happen, as well as on its schedule. list_integrations shows each integration's events.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id
- `events` (array, required): Event ids (server.event)

### `give_tools` (~80 tokens)

Give an agent tools

Give an agent tools that a live integration (or the agency's built-ins) provides, each at a tier.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `agent_id` (string, required): The agent id
- `tools` (array, required)

### `discard_integration` (~99 tokens)

Discard or remove an integration

Throw away a draft (a redraft of a live one goes back to the live version), or remove an added integration entirely. Shipped ones can't be removed.

Input parameters:

- `agency` (string): Which agency: an organization you are in, by name or id (list_agencies). Leave out for your own agency.
- `integration_id` (string, required): The integration id
- `remove_live` (boolean): Remove it even though it is live

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/agency-extremely-agency/extremely-agency-mcp#diagnostics

## Score history

- 2026-11-21: 78
- 2026-11-20: 78
- 2026-11-19: 78
- 2026-11-18: 78
- 2026-11-17: 78
- 2026-11-16: 78
- 2026-11-15: 78
- 2026-11-14: 78
- 2026-11-13: 78
- 2026-11-12: 78
- 2026-11-11: 78
- 2026-11-10: 78
- 2026-11-09: 78
- 2026-11-08: 78
- 2026-11-07: 78
- 2026-11-06: 78
- 2026-11-05: 58

## Common questions

### What is the EXTREMELY agency MCP server?

EXTREMELY agency is an MCP server listed in the public MCP registry as agency.extremely/agency. Your agency of AI agents in your AI app: what agents did, approvals, requests, jobs and reports. This page covers its npm package (@extremely-agency/mcp).

### Is the EXTREMELY agency MCP server safe to use?

EXTREMELY agency scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the EXTREMELY agency MCP server expose?

EXTREMELY agency exposes 31 tools: list_agencies, list_requests, answer_request, reply_to_request, give_task, and 26 more. Their descriptions and schemas cost roughly 4,915 tokens of context every time the server is loaded.

### Is the EXTREMELY agency MCP server still maintained?

EXTREMELY agency is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the EXTREMELY agency MCP server under?

EXTREMELY agency declares the AGPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the EXTREMELY agency MCP server?

VerifyMCP ran 15 checks on EXTREMELY agency, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about EXTREMELY agency: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@extremely-agency/mcp
- Socket report: https://socket.dev/npm/package/@extremely-agency/mcp
- Repository: https://github.com/maxkxd/extremely-autonomous-agents
- Website: https://extremely.agency/
- Changelog RSS feed: https://verifymcp.io/servers/agency-extremely-agency/extremely-agency-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/agency-extremely-agency/extremely-agency-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/agency-extremely-agency/extremely-agency-mcp.json
- HTML version of this page: https://verifymcp.io/servers/agency-extremely-agency/extremely-agency-mcp
