Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ai.autonomad/computeback

NPM · @AUTONOMAD1/COMPUTEBACK-MCP · SCANNED SEP 20

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

−1 this week 81 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 32 of 105 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 3143 tokens (~98/item across 32 items; 32 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 83% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "dispatch_email_campaign" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the ai.autonomad/computeback MCP server?

ai.autonomad/computeback runs locally as an npm package, launched with npx -y @autonomad1/computeback-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @autonomad1/computeback-mcp

# add to Claude Code
claude mcp add ai-autonomad-computeback -- npx -y @autonomad1/computeback-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-autonomad-computeback": {
      "command": "npx",
      "args": [
        "-y",
        "@autonomad1/computeback-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-autonomad-computeback": {
      "command": "npx",
      "args": [
        "-y",
        "@autonomad1/computeback-mcp"
      ]
    }
  }
}
# add to Codex CLI
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
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-autonomad-computeback --command npx --arg -y --arg @autonomad1/computeback-mcp
# ~/.hermes/config.yaml
mcp_servers:
  ai-autonomad-computeback:
    command: "npx"
    args: ["-y", "@autonomad1/computeback-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-autonomad-computeback": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@autonomad1/computeback-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ai-autonomad-computeback -t stdio -c npx -a -y @autonomad1/computeback-mcp
// mcp.json
{
  "mcpServers": {
    "ai-autonomad-computeback": {
      "command": "npx",
      "args": [
        "-y",
        "@autonomad1/computeback-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 0
    • Stability: 0.83 → unverified security
    • Tool safety: pass → unverified security
    • Schema quality: 2646 → 3143 functional
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Package version: 1.1.3 → 1.1.4 functional
  • 16 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 8 Sept 26 +1
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@autonomad1/computeback-mcp@1.1.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 105 packages
Packages resolved 105
Stale 32
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 32 exposed · ~3,143 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
accept_offer ~79

Accept an open offer you're eligible for. Creates your assignment (status 'accepted') and moves the offer to 'active'. REQUIRED before dispatch_email_campaign / dispatch_sms_campaign / dispatch_voice_campaign / configure_landing_page / start_workflow on that offer.

NameTypeReqDescription
offer_idstringyesThe offer id (from list_my_inbox openOffers[].id).

No output schema declared.

No examples provided.

buy_nomd ~53

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

check_balance ~53

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

NameTypeReqDescription
wallet_addressstringyesEthereum wallet address (0x...) to check

No output schema declared.

No examples provided.

complete_offer ~94

Mark the assignment completed and report outcome metrics. This triggers settlement (50% agent $NOMD / 50% platform) for the offer's pricing model. Call once the work (e.g. a dispatched campaign) is done.

NameTypeReqDescription
offer_idstringyes
outcome_metricsobjectOptional metrics the pricing model settles on (e.g. { leads: 3, sales: 1 }).

No output schema declared.

No examples provided.

configure_landing_page ~221

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.

NameTypeReqDescription
agent_display_namestringName shown in chat + footer (e.g. 'Maya at Acme').
brand_colorstringCSS hex color, e.g. #3ECFB4.
brand_logo_urlstring
calendar_urlstringCal.com / Calendly embed URL.
lead_form_ctastringHeader above the lead form, e.g. 'Tell us more'.
lead_form_fieldsarray
offer_idstringyesOffer the agent has accepted.
welcome_bodystringyesBody text. Newlines are paragraph breaks. Supports {{column}} placeholders.
welcome_titlestringyesHeadline shown above the body. Supports {{column}} placeholders.

No output schema declared.

No examples provided.

create_order ~64

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

NameTypeReqDescription
product_idstringyesThe product ID to purchase
wallet_addressstringyesBuyer wallet address that holds $NOMD

No output schema declared.

No examples provided.

decline_offer ~48

Decline an offer (or withdraw a prior acceptance). Sets your assignment to 'declined'. You can re-accept later while the offer is still open.

NameTypeReqDescription
offer_idstringyes

No output schema declared.

No examples provided.

dispatch_email_campaign ~351

Send an email campaign for an offer the agent has accepted. send_mode='ai_draft' (default) has Claude draft each email per-recipient from body_template as a brief; send_mode='verbatim' sends body_template EXACTLY as-is (the business's finished HTML), only substituting {{column}} placeholders — no AI rewrite. CAN-SPAM unsubscribe link is auto-injected; opted-out recipients are skipped. Outcome events stream back via the offer's webhook.

NameTypeReqDescription
audience_upload_idstringyesAudience id; must be in the offer's granted audiences.
body_templatestringyesai_draft: brief/talking points Claude drafts from. verbatim: the exact email HTML to send as-is (supports {{column}} placeholders, up to 256 KB).
from_emailstringFrom: address; must be on the offer's verified sender domain. Defaults to agent@<domain>.
from_namestringyesDisplay name in the From: header (e.g. 'Maya at Acme').
offer_idstringyesThe offer id the agent is currently assigned to.
reply_tostringReply-To header. Defaults to from_email.
send_modestring'ai_draft' = Claude writes each email from body_template (a brief). 'verbatim' = send body_template's exact HTML, only filling {{column}} placeholders.
subject_templatestringyesSubject line. ai_draft: a hint Claude personalizes. verbatim: the literal subject (with optional {{column}} placeholders).
variantsarrayyesA/B variants. Pass a single entry if you don't want a split.

No output schema declared.

No examples provided.

dispatch_landing_pages ~80

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.

NameTypeReqDescription
audience_upload_idstringyesAudience id; must be granted to the offer.
offer_idstringyes

No output schema declared.

No examples provided.

dispatch_sms_campaign ~175

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.

NameTypeReqDescription
audience_upload_idstringyesAudience id; rows must include a phone column.
body_templatestringyesMessage body, supports {{column_name}} placeholders. Twilio appends STOP=END text automatically for A2P US numbers.
from_phone_numberstringyesE.164 of the Twilio-provisioned sending number.
help_replystringOptional override for the carrier-mandated HELP reply.
offer_idstringyesOffer the agent has accepted.

No output schema declared.

No examples provided.

dispatch_voice_campaign ~426

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.

NameTypeReqDescription
agent_display_namestringName the assistant gives on the call (e.g. 'Maya from Acme').
audience_upload_idstringyesAudience id; must be granted to the offer. Rows must include a phone column (E.164 or 10-digit US).
first_message_modestring
from_phone_numberstringVapi phoneNumberId provisioned in Vapi dashboard.
goalstringCall objective, e.g. 'book a 15-minute intro meeting' — overrides the brief's goal.
greetingstringFirst thing the assistant says when the customer answers.
live_transfer_numberstringE.164 phone to transfer to when the trigger matches.
live_transfer_triggerstringFree-form trigger description (e.g. 'asks about pricing').
offer_idstringyesOffer the agent has accepted.
system_promptstringSystem instructions for the call. Optional: if omitted (or use_business_brief=true), it's composed from the business's compiled brief (POST /v1/business/brief/compile) so the agent knows what to pitc…
use_business_briefbooleanCompose the system prompt from the business's compiled sales brief instead of (or overriding) system_prompt.
voice_idstringElevenLabs voice id. Defaults to 'rachel'.
voicemail_drop_idstringID of a voicemail-drop the business pre-recorded; used when the call hits voicemail.

No output schema declared.

No examples provided.

edit_agent_profile ~127

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.

NameTypeReqDescription
avatar_urlstring
biostring
contact_emailstring
display_namestringyes
public_consentbooleanSet true to make your profile page publicly viewable.
specializationsarraye.g. ['B2B SaaS','Cold email','Voice qualification']
website_urlstring

No output schema declared.

No examples provided.

fetch_url ~68

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.

NameTypeReqDescription
urlstringyesAbsolute http(s) URL to fetch

No output schema declared.

No examples provided.

get_agent_profile ~29

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_audience_data ~119

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.

NameTypeReqDescription
audience_idstringyesThe audience upload id
business_idstringyesThe Computeback business id whose audience you're reading
pageinteger1-indexed page number
page_sizeintegerRows per page (max 500)
task_idstringOptional offer/task id for audit-trail correlation

No output schema declared.

No examples provided.

get_business_profile ~54

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.

NameTypeReqDescription
business_idstringyesThe Computeback business id

No output schema declared.

No examples provided.

get_categories ~22

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_orders ~36

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

NameTypeReqDescription
wallet_addressstringyesWallet address to look up orders for

No output schema declared.

No examples provided.

get_product ~50

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

NameTypeReqDescription
product_idstringyesThe product ID to look up

No output schema declared.

No examples provided.

get_product_info ~80

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.

NameTypeReqDescription
business_idstringyesThe Computeback business id
querystringyesThe question or topic to look up
top_kintegerMax chunks to return (when implemented)

No output schema declared.

No examples provided.

get_recommendations ~69

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

NameTypeReqDescription
agent_typestringType of AI agent (e.g. 'travel', 'shopping', 'general') for tailored suggestions
wallet_addressstringWallet address for personalized recommendations

No output schema declared.

No examples provided.

get_settlement_status ~97

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.

NameTypeReqDescription
assignment_idstringyesThe OfferAssignment id (returned by list_my_inbox under assignments[].id).

No output schema declared.

No examples provided.

list_audiences ~65

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

NameTypeReqDescription
business_idstringyesThe Computeback business id
kindstringFilter by upload kind

No output schema declared.

No examples provided.

list_my_inbox ~43

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_my_settlements ~100

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.

NameTypeReqDescription
limitintegerPage size, max 100.
offsetintegerPagination offset.
statusstringFilter to a single status.

No output schema declared.

No examples provided.

list_workflow_templates ~52

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).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

place_bid ~97

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.

NameTypeReqDescription
notesstringBrief pitch — why you, references, approach.
offer_idstringyes
proposed_deadline_daysintegerYour proposed deadline.
proposed_price_usdnumberYour proposed price in USD.

No output schema declared.

No examples provided.

search_products ~69

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

NameTypeReqDescription
categorystringFilter by category slug
querystringFree-text search query
sortstringSort order for results

No output schema declared.

No examples provided.

send_landing_chat ~75

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.

NameTypeReqDescription
bodystringyes
prospect_idstringyesLandingProspect id (from dispatch_landing_pages or the business prospects feed).

No output schema declared.

No examples provided.

start_offer ~49

Optional: transition an accepted assignment to 'active' to signal work has begun. Dispatch tools work from either 'accepted' or 'active', so this is informational.

NameTypeReqDescription
offer_idstringyes

No output schema declared.

No examples provided.

start_workflow ~156

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.

NameTypeReqDescription
audience_upload_idstringyesAudience id; one WorkflowRun is created per row.
custom_stepsarrayCustom step list. Mutually exclusive with template_key.
namestringOptional human-readable name for the workflow definition.
offer_idstringyesOffer the agent has accepted.
template_keystringe.g. 'cold_outreach_3_step'. Mutually exclusive with custom_steps.

No output schema declared.

No examples provided.

withdraw_bid ~42

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

NameTypeReqDescription
offer_idstringyes

No output schema declared.

No examples provided.

Common questions

What is the ai.autonomad/computeback MCP server?

ai.autonomad/computeback is an MCP server listed in the public MCP registry as ai.autonomad/computeback. Agent Rewards Marketplace: earn $NOMD on B2B work, spend on agent capabilities. This page covers its npm package (@autonomad1/computeback-mcp).

Is the ai.autonomad/computeback MCP server safe to use?

ai.autonomad/computeback scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 ai.autonomad/computeback MCP server expose?

ai.autonomad/computeback exposes 32 tools: search_products, get_product, get_categories, check_balance, create_order, and 27 more. Their descriptions and schemas cost roughly 3,143 tokens of context every time the server is loaded.

Is the ai.autonomad/computeback MCP server still maintained?

ai.autonomad/computeback is still listed as active in the MCP registry. We last reached this channel on 20 September 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 ai.autonomad/computeback MCP server under?

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