# Forbiz (npm · forbiz-mcp)

CRM for AI agents: commitments, expected signals, evidence and outcomes agents resume.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `forbiz-mcp`: 77/100 (this document), [markdown](https://verifymcp.io/servers/tbernabo-forbiz-mcp/forbiz-mcp.md), [page](https://verifymcp.io/servers/tbernabo-forbiz-mcp/forbiz-mcp)

## Channel facts

- Registry: `npm`
- Package: `forbiz-mcp`
- Version: `0.1.0`
- 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 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 24 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1728 tokens (~86/item across 20 items; 20 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 73/100
  - Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% 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.
  - We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 21 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.

## Install

### How do I install the Forbiz MCP server?

Forbiz runs locally as an npm package, launched with npx -y forbiz-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 tbernabo-forbiz-mcp -- npx -y forbiz-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "tbernabo-forbiz-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "forbiz-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tbernabo-forbiz-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "forbiz-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add tbernabo-forbiz-mcp -- npx -y forbiz-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add tbernabo-forbiz-mcp --command npx --arg -y --arg forbiz-mcp
```

### Hermes

```yaml
mcp_servers:
  tbernabo-forbiz-mcp:
    command: "npx"
    args: ["-y", "forbiz-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "tbernabo-forbiz-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "forbiz-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add tbernabo-forbiz-mcp -t stdio -c npx -a -y forbiz-mcp
```

### Other

```json
{
  "mcpServers": {
    "tbernabo-forbiz-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "forbiz-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.

### 2026-11-05 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 70, +3)

- [functional improvement] Stability: unverified → 0.27

## MCP tools (20)

### `forbiz_start` (~126 tokens)

Open a Forbiz workspace

Open a provisional Forbiz workspace with no account, no email and no human (POST /bootstrap). The credential is stored locally by this server and never shown. Returns the workspace, the trial limits and a claim link for the owner. Call it once; if a credential already exists it refuses unless replace is true.

Input parameters:

- `agent_name` (string, required): Your name as an agent, e.g. 'Acme ops agent'
- `replace` (boolean): Open a new workspace even if a credential is already stored
- `workspace_name` (string): Name of the business or workspace

### `forbiz_me` (~32 tokens)

Who am I in Forbiz

Workspace, agent identity, capabilities, plan and limits of the current credential (GET /me). Call this first.

### `forbiz_claim_link` (~43 tokens)

Get the owner's claim link

A link the human owner opens to take ownership of a provisional workspace (POST /claim-link). Give it to the owner; the agent keeps working after the claim.

### `forbiz_next` (~26 tokens)

Next move

The single next thing that needs attention, with its handoff (GET /next).

### `forbiz_prompts` (~62 tokens)

Queue of pending items

Everything waiting, grouped (needs_decision, needs_feedback, waiting, needs_review_date), each with timing.available_commands: what you may do right now (GET /prompts).

Input parameters:

- `group` (string): Only one group, e.g. needs_feedback

### `forbiz_state` (~25 tokens)

Workspace state

Overview of the workspace: queues, counts and next priorities (GET /state).

### `forbiz_search` (~72 tokens)

Search Forbiz

Full-text search across actions, evidence, people, organizations, projects, outreach and decisions (GET /search). To resume a commitment by its key, use forbiz_commit with the same commitmentKey instead: the 409 returns it.

Input parameters:

- `q` (string, required): Search terms
- `type` (string)

### `forbiz_agents` (~63 tokens)

Agents of this workspace

Every agent of this workspace with its activity and a plain track record over the actions it created: created, executed, signal recorded, outcomes, overdue (GET /agents). Counts only, no ranking.

Input parameters:

- `days` (integer): Window in days, default 30

### `forbiz_commit` (~303 tokens)

Record a commitment

Record an action you will take or took, with the signal you expect back (POST /actions). Always send a commitmentKey (a short stable id for the objective, e.g. 'acme/quote-followup') and expectedSignalAt. A second open commitment with the same key is refused 409 COMMITMENT_ALREADY_OPEN and the body returns the open one: that is how you resume. A look-alike is refused 409 POSSIBLE_DUPLICATE: resend with confirm_new true only if it is a different objective.

Input parameters:

- `commitmentKey` (string): Stable id of the objective this commitment serves (recommended)
- `confirm_new` (boolean): Override a POSSIBLE_DUPLICATE refusal
- `description` (string, required): What the action is, in one sentence
- `dueAt` (string): When the action itself is due; without it the action never becomes overdue
- `expectedSignal` (string): What you expect to see if it worked, e.g. 'Dana replies with a date'
- `expectedSignalAt` (string): When the expected signal should have arrived
- `expectedSignalSource` (object): Where the expected signal will appear
- `projectId` (string): UUID of an existing project in this workspace
- `roi` (object): What it is worth, each dimension 0-5. Optional; never inferred by Forbiz
- `verb` (string)
- `whyThisMove` (string)

### `forbiz_get_action` (~41 tokens)

Read one action

Full state of one action: expected signal, dates, lifecycle, outcome (GET /actions/{id}).

Input parameters:

- `id` (string, required): Action id

### `forbiz_action_history` (~41 tokens)

History of one action

Chronological changes of one action and who made each one, agent or human (GET /actions/{id}/history).

Input parameters:

- `id` (string, required)

### `forbiz_mark_executed` (~104 tokens)

Mark an action as executed

Record that the action really happened (POST /actions/{id}/execute). Only when it did: never mark as executed without evidence that the act occurred.

Input parameters:

- `executedAt` (string): When it really happened; at most 5 minutes in the future
- `expectedSignalAt` (string): ISO 8601 date-time, e.g. 2026-10-15T14:00:00Z
- `id` (string, required)

### `forbiz_record_signal` (~75 tokens)

Record the signal that came back

Record what actually happened after the action (POST /signals). A signal is written once; a correction is a new record.

Input parameters:

- `actionId` (string, required)
- `actualSignal` (string, required): What actually came back, in plain words
- `learningNote` (string)
- `outcomeStatus` (string)

### `forbiz_check_signal` (~155 tokens)

Record a signal check

Record that you looked for the expected signal (POST /actions/{id}/signal-checks). not_found_in_source REQUIRES source and period: it says where you looked and when, never that a third party did not answer. found closes nothing; link the signal with forbiz_record_signal. cannot_check REQUIRES reason.

Input parameters:

- `id` (string, required): Action id
- `looked_for` (string)
- `note` (string)
- `period` (object): The time window you checked
- `reason` (string)
- `result` (string, required)
- `source` (object): Where you looked, e.g. { kind: 'email_thread', detail: 'Re: quote' }

### `forbiz_postpone` (~74 tokens)

Move the expected signal date

Push the date the signal is expected (POST /actions/{id}/postpone).

Input parameters:

- `expectedSignalAt` (string, required): ISO 8601 date-time, e.g. 2026-10-15T14:00:00Z
- `id` (string, required)
- `reason` (string)

### `forbiz_close` (~48 tokens)

Close the loop

Resolve an action with its outcome (POST /actions/{id}/close-loop).

Input parameters:

- `id` (string, required)
- `learningNote` (string)
- `outcomeStatus` (string, required)

### `forbiz_close_without_signal` (~68 tokens)

Close without a signal

Close an action that will not get a signal, saying why (POST /actions/{id}/close-without-signal). Silence is not rejection: say what you know.

Input parameters:

- `id` (string, required)
- `learningNote` (string)
- `reason` (string)

### `forbiz_add_evidence` (~59 tokens)

Record evidence

Append what you observed, were told, inferred or decided (POST /context/evidence). Append-only epistemic history: nothing becomes workspace truth automatically, and a contradiction never erases what it contradicts.

Input parameters:

- `items` (array, required)

### `forbiz_find_evidence` (~75 tokens)

Find evidence

Recover evidence by text or subject (GET /context/evidence). Each item carries its source and its contradiction and supersession pointers.

Input parameters:

- `materialOnly` (boolean)
- `q` (string): Full text over subject and content
- `status` (string)
- `subject` (string): Subject contains this

### `forbiz_request` (~109 tokens)

Call any Forbiz route

Escape hatch for any other route of the Forbiz Agent API (https://forbiz.io/openapi.json): projects, decisions, delegations, outreach, policies, export, purchases. The path is relative to the API base, e.g. '/projects' or '/decisions/recommendation'. Forbiz enforces capabilities server-side.

Input parameters:

- `body` (object)
- `method` (string, required)
- `path` (string, required): Route path starting with /
- `query` (object)

## Diagnostics

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

## Score history

- 2026-11-05: 77
- 2026-11-04: 76
- 2026-11-03: 76
- 2026-11-02: 75
- 2026-11-01: 75
- 2026-10-31: 75
- 2026-10-30: 74
- 2026-10-29: 74
- 2026-10-28: 73
- 2026-10-27: 73
- 2026-10-26: 72
- 2026-10-25: 72
- 2026-10-24: 71
- 2026-10-23: 71
- 2026-10-22: 70
- 2026-10-21: 67
- 2026-10-20: 67
- 2026-10-19: 67
- 2026-10-18: 67
- 2026-10-17: 67
- 2026-10-16: 67
- 2026-10-15: 67
- 2026-10-14: 67
- 2026-10-13: 38
- 2026-10-12: 38

## Common questions

### What is the Forbiz MCP server?

Forbiz is an MCP server listed in the public MCP registry as io.github.tbernabo/forbiz-mcp. CRM for AI agents: commitments, expected signals, evidence and outcomes agents resume. This page covers its npm package (forbiz-mcp).

### Is the Forbiz MCP server safe to use?

Forbiz scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. 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 Forbiz MCP server expose?

Forbiz exposes 20 tools: forbiz_start, forbiz_me, forbiz_claim_link, forbiz_next, forbiz_prompts, and 15 more. Their descriptions and schemas cost roughly 1,601 tokens of context every time the server is loaded.

### Is the Forbiz MCP server still maintained?

Forbiz is still listed as active in the MCP registry. We last reached this channel on 5 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 Forbiz MCP server under?

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

## Links

- npm package: https://www.npmjs.com/package/forbiz-mcp
- Socket report: https://socket.dev/npm/package/forbiz-mcp
- Repository: https://github.com/tbernabo/forbiz-mcp
- Website: https://forbiz.io/
- Changelog RSS feed: https://verifymcp.io/servers/tbernabo-forbiz-mcp/forbiz-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/tbernabo-forbiz-mcp/forbiz-mcp.json
- HTML version of this page: https://verifymcp.io/servers/tbernabo-forbiz-mcp/forbiz-mcp