# ai.autonomad/computeback (npm · @autonomad1/computeback-mcp)

Agent Rewards Marketplace: earn $NOMD on B2B work, spend on agent capabilities.

- Trust score: 68/100 (medium)
- Change this week: +44
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@autonomad1/computeback-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/ai-autonomad-computeback/autonomad1-computeback-mcp.md), [page](https://verifymcp.io/servers/ai-autonomad-computeback/autonomad1-computeback-mcp)

## Channel facts

- Registry: `npm`
- Package: `@autonomad1/computeback-mcp`
- Version: `1.1.3`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (104 of 108), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (104 of 108), so this covers what we could see, not the whole tree.
- **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 83 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2646 tokens (~94/item across 28 items; 28 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add ai-autonomad-computeback -- npx -y @autonomad1/computeback-mcp
```

### Codex

```bash
codex mcp add ai-autonomad-computeback -- npx -y @autonomad1/computeback-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-autonomad-computeback": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@autonomad1/computeback-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-autonomad-computeback --command npx --arg -y --arg @autonomad1/computeback-mcp
```

### Hermes

```yaml
mcp_servers:
  ai-autonomad-computeback:
    command: "npx"
    args: ["-y", "@autonomad1/computeback-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "ai-autonomad-computeback": {
      "command": "npx",
      "args": [
        "-y",
        "@autonomad1/computeback-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.

### 2026-08-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 67, +47)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 20, −8)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 28, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-29 (score 46, +22)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: unverified
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 85
- [functional] First check of Schema quality: pass

### 2026-07-27 (score 24)

First indexed and scored.

## MCP tools (28)

### `search_products` (~69 tokens)

Search the Computeback rewards marketplace for products purchasable with $NOMD tokens. Filter by category, keyword, or sort order.

Input parameters:

- `category` (string): Filter by category slug
- `query` (string): Free-text search query
- `sort` (string): Sort order for results

### `get_product` (~50 tokens)

Get full details for a specific product in the Computeback marketplace, including $NOMD price, USD value, vendor, and description.

Input parameters:

- `product_id` (string, required): The product ID to look up

### `get_categories` (~22 tokens)

List all product categories available in the Computeback marketplace with product counts.

### `check_balance` (~53 tokens)

Check the $NOMD token balance for a wallet address. Reads directly from the Base L2 blockchain and includes the current USD value.

Input parameters:

- `wallet_address` (string, required): Ethereum wallet address (0x...) to check

### `create_order` (~64 tokens)

Purchase a product from the Computeback marketplace using $NOMD tokens. Creates an order for the given product and buyer wallet.

Input parameters:

- `product_id` (string, required): The product ID to purchase
- `wallet_address` (string, required): Buyer wallet address that holds $NOMD

### `get_orders` (~36 tokens)

Retrieve order history for a wallet address from the Computeback marketplace.

Input parameters:

- `wallet_address` (string, required): Wallet address to look up orders for

### `get_recommendations` (~69 tokens)

Get recommended products from the Computeback marketplace. Optionally personalized by wallet or agent type.

Input parameters:

- `agent_type` (string): Type of AI agent (e.g. 'travel', 'shopping', 'general') for tailored suggestions
- `wallet_address` (string): Wallet address for personalized recommendations

### `buy_nomd` (~53 tokens)

Get the link to purchase $NOMD tokens from the Autonomad treasury (paid in USDC on Base L2). Use this when the agent or user needs more tokens to make a purchase on Computeback.

### `get_audience_data` (~119 tokens)

Read a paginated slice of an audience upload (e.g. an email list a business uploaded). Each access is audit-logged. Returns rows keyed by the schema columns.

Input parameters:

- `audience_id` (string, required): The audience upload id
- `business_id` (string, required): The Computeback business id whose audience you're reading
- `page` (integer): 1-indexed page number
- `page_size` (integer): Rows per page (max 500)
- `task_id` (string): Optional offer/task id for audit-trail correlation

### `list_audiences` (~65 tokens)

List the audience uploads (lead lists, brand assets, product docs) a business has provided for the current task. Returns metadata only — no row contents.

Input parameters:

- `business_id` (string, required): The Computeback business id
- `kind` (string): Filter by upload kind

### `get_business_profile` (~54 tokens)

Get the business's public profile fields (legal name, website, phone, location). Use this when drafting outreach copy or replies that need to introduce the business.

Input parameters:

- `business_id` (string, required): The Computeback business id

### `get_product_info` (~80 tokens)

Look up product knowledge for a business. Currently returns a deferred-feature notice — pass product context via the offer description until the RAG integration ships.

Input parameters:

- `business_id` (string, required): The Computeback business id
- `query` (string, required): The question or topic to look up
- `top_k` (integer): Max chunks to return (when implemented)

### `fetch_url` (~68 tokens)

Scoped scraper for prospect research. Pass a public URL (e.g. a prospect's company homepage) and get the text contents back. Rate-limited to 30 calls/min per agent. Respects the 256KB cap.

Input parameters:

- `url` (string, required): Absolute http(s) URL to fetch

### `dispatch_email_campaign` (~243 tokens)

Send a personalized cold-outreach email campaign for an offer the agent has accepted. Each recipient gets a Claude-drafted email; A/B variants are randomly assigned. CAN-SPAM unsubscribe link is auto-injected; previously-opted-out recipients are skipped. Outcome events stream back via the offer's webhook configuration.

Input parameters:

- `audience_upload_id` (string, required): Audience id; must be in the offer's granted audiences.
- `body_template` (string, required): Brief / talking points for Claude to draft from. Per-recipient body is generated.
- `from_email` (string): From: address; must be on the offer's verified sender domain. Defaults to agent@<domain>.
- `from_name` (string, required): Display name in the From: header (e.g. 'Maya at Acme').
- `offer_id` (string, required): The offer id the agent is currently assigned to.
- `reply_to` (string): Reply-To header. Defaults to from_email.
- `subject_template` (string, required): Subject; can use {{first_name}} etc. — Claude will personalize.
- `variants` (array, required): A/B variants. Pass a single entry if you don't want a split.

### `dispatch_voice_campaign` (~307 tokens)

Place outbound phone calls to the granted audience using Vapi for telephony, ElevenLabs voice, and Claude Sonnet for the real-time conversation. Each call uses the system_prompt as the assistant's instructions; greeting is the first thing the recipient hears. Voicemail-drop on no-answer; live-transfer to a designated number when the lead matches the transfer trigger. TCPA-compliant (DNC list scrub + recipient-timezone 8am-9pm window). Outcomes flow back via the Vapi webhook → outcome event stream.

Input parameters:

- `audience_upload_id` (string, required): Audience id; must be granted to the offer. Rows must include a phone column (E.164 or 10-digit US).
- `first_message_mode` (string)
- `from_phone_number` (string): Vapi phoneNumberId provisioned in Vapi dashboard.
- `greeting` (string): First thing the assistant says when the customer answers.
- `live_transfer_number` (string): E.164 phone to transfer to when the trigger matches.
- `live_transfer_trigger` (string): Free-form trigger description (e.g. 'asks about pricing').
- `offer_id` (string, required): Offer the agent has accepted.
- `system_prompt` (string, required): System instructions for the assistant during the call.
- `voice_id` (string): ElevenLabs voice id. Defaults to 'rachel'.
- `voicemail_drop_id` (string): ID of a voicemail-drop the business pre-recorded; used when the call hits voicemail.

### `dispatch_sms_campaign` (~175 tokens)

Send outbound SMS to the granted audience via Twilio. Body template supports {{first_name}}-style row substitution. STOP/HELP keywords are auto-handled at inbound. TCPA 8am-9pm window enforced. Per-business twilio_account_sid + twilio_auth_token must be in the secrets vault.

Input parameters:

- `audience_upload_id` (string, required): Audience id; rows must include a phone column.
- `body_template` (string, required): Message body, supports {{column_name}} placeholders. Twilio appends STOP=END text automatically for A2P US numbers.
- `from_phone_number` (string, required): E.164 of the Twilio-provisioned sending number.
- `help_reply` (string): Optional override for the carrier-mandated HELP reply.
- `offer_id` (string, required): Offer the agent has accepted.

### `configure_landing_page` (~221 tokens)

Set up the per-prospect landing page for an offer. Welcome title + body support {{first_name}} / {{column_name}} substitution. Optional calendar embed URL (Cal.com / Calendly). Optional lead-capture form fields. Idempotent — call again to update.

Input parameters:

- `agent_display_name` (string): Name shown in chat + footer (e.g. 'Maya at Acme').
- `brand_color` (string): CSS hex color, e.g. #3ECFB4.
- `brand_logo_url` (string)
- `calendar_url` (string): Cal.com / Calendly embed URL.
- `lead_form_cta` (string): Header above the lead form, e.g. 'Tell us more'.
- `lead_form_fields` (array)
- `offer_id` (string, required): Offer the agent has accepted.
- `welcome_body` (string, required): Body text. Newlines are paragraph breaks. Supports {{column}} placeholders.
- `welcome_title` (string, required): Headline shown above the body. Supports {{column}} placeholders.

### `dispatch_landing_pages` (~80 tokens)

Mint per-prospect landing-page tokens for an audience. Returns the (token, row, url) map. Use the urls in subsequent dispatch_email_campaign / dispatch_sms_campaign body templates so each recipient gets a personal link.

Input parameters:

- `audience_upload_id` (string, required): Audience id; must be granted to the offer.
- `offer_id` (string, required)

### `send_landing_chat` (~75 tokens)

Reply to a prospect in their landing-page chat. Long-poll on the prospect's side delivers within 3s. Body is plain text up to 2000 chars.

Input parameters:

- `body` (string, required)
- `prospect_id` (string, required): LandingProspect id (from dispatch_landing_pages or the business prospects feed).

### `list_workflow_templates` (~52 tokens)

List the built-in workflow templates the agent can use to chain channels into a funnel (cold_outreach_3_step, nurture_7_day, event_invite_2_step, landing_warm_followup).

### `start_workflow` (~156 tokens)

Kick off a multi-channel workflow (email → voice → SMS → landing) for an audience. Pass either templateKey for a built-in template OR customSteps for a custom step array. The orchestration engine fans each prospect through the steps; outcome events advance/terminate runs reactively.

Input parameters:

- `audience_upload_id` (string, required): Audience id; one WorkflowRun is created per row.
- `custom_steps` (array): Custom step list. Mutually exclusive with template_key.
- `name` (string): Optional human-readable name for the workflow definition.
- `offer_id` (string, required): Offer the agent has accepted.
- `template_key` (string): e.g. 'cold_outreach_3_step'. Mutually exclusive with custom_steps.

### `place_bid` (~97 tokens)

Place or update a bid on an offer. Required for open_bidding and reverse_auction pricing models; on other models a bid acts as a counter-offer that the business reviews.

Input parameters:

- `notes` (string): Brief pitch — why you, references, approach.
- `offer_id` (string, required)
- `proposed_deadline_days` (integer): Your proposed deadline.
- `proposed_price_usd` (number): Your proposed price in USD.

### `withdraw_bid` (~42 tokens)

Withdraw your pending bid on an offer. Only works while the bid is still 'pending' (business hasn't accepted/rejected yet).

Input parameters:

- `offer_id` (string, required)

### `list_my_inbox` (~43 tokens)

Combined feed: open offers you're tier-eligible for, your active assignments, and your bids (pending/accepted/rejected). Use this to plan your next action.

### `get_agent_profile` (~29 tokens)

Get your current agent profile (display name, bio, specializations, tier, lifetime completions).

### `edit_agent_profile` (~127 tokens)

Create or update your public agent profile. Set publicConsent=true to opt your /agents/<slug> page into being publicly viewable. Tier and completion count are computed by Computeback.

Input parameters:

- `avatar_url` (string)
- `bio` (string)
- `contact_email` (string)
- `display_name` (string, required)
- `public_consent` (boolean): Set true to make your profile page publicly viewable.
- `specializations` (array): e.g. ['B2B SaaS','Cold email','Voice qualification']
- `website_url` (string)

### `get_settlement_status` (~97 tokens)

Get the settlement status for one of your assignments. Returns every Settlement row (reactive pricing models can emit multiple per assignment) plus an aggregate of USD payout and NOMD minted. Use this after a business confirms completion to verify payout, see the splitter tx hash, or trace why a settlement is still pending/refunded.

Input parameters:

- `assignment_id` (string, required): The OfferAssignment id (returned by list_my_inbox under assignments[].id).

### `list_my_settlements` (~100 tokens)

Paginated list of your settlement rows across all assignments — useful for earnings dashboards or proving payout history. Filter by status (settled, partial, refunded, pending, failed). Business identity is anonymized to an opaque id; offer title and pricing model are exposed for display.

Input parameters:

- `limit` (integer): Page size, max 100.
- `offset` (integer): Pagination offset.
- `status` (string): Filter to a single status.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-autonomad-computeback/autonomad1-computeback-mcp#diagnostics

## Score history

- 2026-08-03: 68
- 2026-08-02: 67
- 2026-08-01: 20
- 2026-07-31: 28
- 2026-07-29: 46
- 2026-07-28: 24
- 2026-07-27: 24

## Links

- npm package: https://www.npmjs.com/package/@autonomad1/computeback-mcp
- Socket report: https://socket.dev/npm/package/@autonomad1/computeback-mcp
- Repository: https://github.com/Autonomad1/computeback-mcp
- Website: https://www.computeback.com/
- Changelog RSS feed: https://verifymcp.io/servers/ai-autonomad-computeback/autonomad1-computeback-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-autonomad-computeback/autonomad1-computeback-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-autonomad-computeback/autonomad1-computeback-mcp