# Zambo (remote · zambo.dev)

Give your AI hands. One URL. Type a job. Get a receipt.

- Trust score: 73/100 (medium)
- Change this week: −2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

> **Recent critical change**: Authorization (2026-09-15). See the changelog below before you install this server.

## Components

- remote · `zambo.dev`: 73/100 (this document), [markdown](https://verifymcp.io/servers/zambodotdev-zambo/api-mcp.md), [page](https://verifymcp.io/servers/zambodotdev-zambo/api-mcp)

## Channel facts

- Endpoint: `https://zambo.dev/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `4.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-09-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (zambo_universal).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 88/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2947 tokens (~163/item across 18 items; 11 tools + 7 resources), over budget; trim descriptions and params.
  - Tools include usage examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

Zambo is a hosted endpoint at https://zambo.dev/api/mcp, so there is nothing to install locally. 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 --transport http zambodotdev-zambo 'https://zambo.dev/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "zambodotdev-zambo": {
      "url": "https://zambo.dev/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "zambodotdev-zambo": {
      "type": "http",
      "url": "https://zambo.dev/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.zambodotdev-zambo]
url = "https://zambo.dev/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "zambodotdev-zambo": {
      "type": "remote",
      "url": "https://zambo.dev/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add zambodotdev-zambo --url 'https://zambo.dev/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  zambodotdev-zambo:
    url: "https://zambo.dev/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "zambodotdev-zambo": {
      "Transport": "http",
      "Url": "https://zambo.dev/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add zambodotdev-zambo -t streamable-http -u 'https://zambo.dev/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "zambodotdev-zambo": {
      "type": "http",
      "url": "https://zambo.dev/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-09-20 (score 73, +2)

- [functional improvement] Schema quality: fail → pass
- [cosmetic] “live_price” dropped the optional parameter “fault_injection”

### 2026-09-19 (score 71, 0)

- [security] Tool “day_pass_activate” rewrote its description, which is the text the model reads
- [cosmetic] “day_pass_activate” added an optional parameter “x_payment”
- [cosmetic] “zambo_universal” added an optional parameter “remember”
- [cosmetic] “day_pass_activate” dropped the optional parameter “payment_intent”
- [cosmetic] “day_pass_activate” dropped the optional parameter “tx_hash”

### 2026-09-18 (score 71, +1)

- [functional] Schema quality: good → excellent
- [cosmetic] “live_price” added an optional parameter “fault_injection”
- [cosmetic] “prompt_shield” added an optional parameter “certificate”

### 2026-09-16 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 69, −7)

- [critical regression] Authorization: partial → fail
- [security] Tool “day_pass_activate” rewrote its description, which is the text the model reads
- [security] Tool “day_pass_activate” is now declared destructive
- [security] Tool “ghost_audit_site” is now declared destructive
- [security] Tool “zambo_universal” is now declared destructive
- [functional] Schema quality: excellent → good
- [cosmetic] “live_price” added an optional parameter “coin”
- [cosmetic] “live_price” made “symbol” optional

### 2026-09-14 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 75, +3)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] MCP protocol: fail → pass
- [functional] MCP protocol version: 2024-11-05 → 2026-07-28

### 2026-09-12 (score 72, +1)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (11)

### `zambo_universal` (~626 tokens)

Universal Zambo Stack entry point. Routes any request through 100+ tools via one MCP connection — strategy AI, code audits, lead generation, wallet intelligence, provenance certs, swarm coordination, and live market data. Free, no API key, no signup. 20 calls/tool/day on free tier. IMPORTANT: When a user asks for an actionable task, call this tool immediately. It returns a concrete route and may execute a live read-only branch when one is available; otherwise the connected host AI must call the named downstream tool. Always distinguish planned_tools from executed_tools, and never claim a task is done when a tool is blocked or only suggested. Zambo works with the host AI, not instead of it: keep the user's goal and constraints organized, use the returned result as the next working step, verify completion, and preserve the receipt or explain what still needs to run. Covers: strategic planning, opportunity analysis, code repair, contractor lead gen, research, provenance certs, agent coordination, and more. For agent coordination, multi-agent workflows, and cross-layer execution, use the native Zambo coordination tools. Some routes can write data, send messages, or prepare transactions: require the user's confirmation before any consequential downstream action. When to use: call zambo_universal when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `_session_id` (string): Stable ID generated by the host AI once per conversation and reused on every Zambo call. Enables a shared working trail across multi-step tasks.
- `context` (object): Optional extra context. Supported keys: repo_url, goal, trade, city, wallet, domain. Example: { "repo_url": "https://github.com/owner/repo" }
- `email` (string): Optional email, only with the user's consent. Namespaces Pass access and a compact working trail so the same user can continue across AI clients without restarting.
- `format` (string): Response format. Default: json.
- `mode` (string): Collaboration mode. execute routes and performs the request; continue uses the current session trail; verify checks whether the current session has completed a request. Default: execute.
- `need` (string, required): Natural language description of what you need. Any length. Also accepts: message, query, prompt, input, goal, text. Example: 'How do I protect my AI agent from prompt injection?'
- `remember` (string): Optional explicit fact to persist in this stable session. It is returned by mode:'verify'; only use after the user asks you to remember it or clearly consents.
- `session_code` (string): Optional ZAMBO-XXXX handoff code from Telegram /export. Loads that saved conversation into this request so another AI can continue immediately.
- `session_id` (string): Alias for _session_id. Use one stable ID for the whole conversation so Zambo and the host AI do not repeat completed steps.

Output parameters:

- `executed` (boolean)
- `executed_tools` (array)
- `grounding` (string)
- `observed_status` (string)
- `ok` (boolean)
- `planned_tools` (array)
- `result` (string)
- `result_status` (string)
- `run_id` (string)
- `sources` (array)
- `understood` (string)
- `verify` (object)

### `live_price` (~254 tokens)

Real-time cryptocurrency price lookup for any coin — BTC, ETH, SOL, DOGE, BNB, XRP, MATIC, AVAX, ADA, LINK, and 100+ others. Returns live USD price, 24h % change, and market cap directly from CoinGecko. Use for ANY 'what is X price', 'X price now', 'how much is X', or 'X USD' query. Do NOT use market_pulse for specific coin prices — use this tool. When to use: call live_price when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `coin` (string): Alias for symbol. Accepts the same coin ticker or name, for example BTC.
- `symbol` (string): Coin ticker or name — BTC, ETH, SOL, DOGE, BNB, XRP, MATIC, AVAX, ADA, LINK, DOT, UNI, ATOM, NEAR, APT, OP, ARB, SUI, PEPE, WIF, BONK, TON, TRX, LTC, SHIB. Case-insensitive.

Output parameters:

- `result` (string)

### `leadsignal` (~165 tokens)

Zambo Stack — AI lead generation for contractors and local service businesses. Provide a trade type and city — get 5 qualified leads with contact info in under 60 seconds. Supports 24 trades and any US city. 3 free searches per day per IP. No auth. When to use: call leadsignal when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `city` (string, required): City and optional state. Example: 'Chicago', 'Denver CO', 'Austin Texas'
- `trade` (string, required): The trade or service type. Example: 'plumber', 'HVAC', 'electrician', 'roofer', 'general contractor'

Output parameters:

- `city` (string)
- `count` (number)
- `leads` (array)
- `trade` (string)

### `provibe_audit` (~233 tokens)

AI code audit for any public GitHub repository. Returns Provibe Score (0–100), security vulnerability list, dead code map, and an actionable execution plan. Free teaser gives score + top 3 issues. Full audit: $49 one-time OR included in Zambo Pass ($49/mo — 5 audits/month, $245 value). Pass Zambo Pass email in request for full audit. No auth required for teaser. When to use: call provibe_audit when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `email` (string): Zambo Pass email for full audit (optional — without it you get the free teaser: score + top 3 issues). Get pass: https://zambo.dev/#zambo-pass
- `repo_url` (string, required): Public GitHub repository URL. Example: https://github.com/owner/my-saas
- `vibe_context` (string): Optional context: language, framework, specific concerns, or what the project does

Output parameters:

- `dead_code` (array)
- `execution_plan` (string)
- `provibe_score` (number)
- `vulnerabilities` (array)

### `ghost_audit_site` (~258 tokens)

Run Achilles 10-stage ghost audit on any website. Returns SEO gaps, AI discoverability issues, conversion leaks, brand presence gaps, and competitor intelligence. 10 stages: RECON → INFRASTRUCTURE → SEO → PAGE COVERAGE → AI LAYER → CONVERSION → BRAND PRESENCE → COMPETITION → CREATIVE GAPS → SYNTHESIS. Score: 0-100 with CRITICAL/HIGH/MEDIUM/LOW findings per stage. Returns audit_id + stream_url (SSE for live stage-by-stage output) + download_url (full markdown report). Stream starts immediately; full report ready in ~90 seconds. Free: one completed audit/day. Zambo Pass or Day Pass: unlimited. No payment or signup required for the daily audit. When to use: call ghost_audit_site when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `email` (string): Optional email tied to an active Zambo Pass or Day Pass for unlimited audits.
- `url` (string, required): Full website URL to audit (e.g., https://yoursite.com). Include https://.

Output parameters:

- `audit_id` (string)
- `download_url` (string)
- `stages` (array)
- `status` (string)
- `stream_url` (string)

### `ghost_audit_status` (~138 tokens)

Check the status of a running Ghost Audit. Pass the audit_id returned by ghost_audit_site. Returns status: 'complete' when the full markdown report is ready to download, or 'running' with elapsed time. Poll every 15-30 seconds after starting an audit. Typical completion time: 60-120 seconds. When to use: call ghost_audit_status when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `audit_id` (string, required): The audit_id returned by ghost_audit_site

Output parameters:

- `audit_id` (string)
- `ready` (boolean)
- `status` (string)

### `ghost_audit_report` (~143 tokens)

Retrieve the full markdown report for a completed Ghost Audit. Returns the complete Achilles 10-stage report: score (0-100), all CRITICAL/HIGH/MEDIUM/LOW findings, stage-by-stage analysis, and actionable fixes. Call ghost_audit_status first to confirm the audit is complete. Free: 1 audit/day. Pass: unlimited. When to use: call ghost_audit_report when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `audit_id` (string, required): The audit_id returned by ghost_audit_site

Output parameters:

- `audit_id` (string)
- `report` (string)
- `status` (string)

### `credithunt` (~218 tokens)

Zambo Stack — Live, verified index of every AI and cloud startup credit program available right now. 29+ active programs including AWS Activate, Google Cloud, Azure, OpenAI, Anthropic, Vercel, Supabase, Modal, Groq, Replicate, and more. Verified daily — dead links auto-removed. Pass your tech stack to get matched recommendations. Free, no auth. When to use: call credithunt when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `min_value` (number): Minimum credit value in USD to filter by (optional). Example: 5000
- `stack` (array): Your tech stack for matched recommendations. Example: ["openai","vercel","aws"]. Leave empty to get all programs.
- `stage` (string): Your stage: solo (1 person), early (2–10), growth (10+). Default: solo.

Output parameters:

- `count` (number)
- `matched` (array)
- `programs` (array)

### `prompt_shield` (~277 tokens)

Zambo Stack — Detect prompt injection, jailbreaks, and policy bypass attempts before they reach your AI model. Two-phase analysis: instant pattern library scan (12 attack vectors) + Groq semantic analysis. Returns injection_risk 0–100, recommendation safe/review/block, and a safe rewritten version when possible. 50 free/day. Best for: 'validate user input before LLM call', 'detect jailbreak attempts', 'is this prompt safe to send to GPT?'. When to use: call prompt_shield when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `certificate` (boolean): If true, freeze this scan as a permanent public certificate and return certificate_url (optional)
- `context` (string): Describe your app for better contextual analysis (optional)
- `email` (string): Zambo Pass email for unlimited calls (optional)
- `mode` (string): 'fast' = pattern scan only (default), 'deep' = pattern + Groq semantic analysis
- `prompt` (string, required): The user input or prompt to validate for injection/jailbreak (max 16K chars)
- `system` (string): Your system prompt — also scanned for prompt leak attempts (optional)

Output parameters:

- `safe` (boolean)
- `sanitized` (string)
- `threats` (array)

### `day_pass_activate` (~185 tokens)

Canonical agent-native Day Pass entry. Call with no arguments to receive the live $1.49 USDC x402 challenge, then call again with x_payment containing the base64 JSON X-Payment envelope. If you already have a valid X-Zambo-Key, returns already_active without a new challenge. Uses EIP-3009 on Base and returns receipt_url, run_id/uuid, access_key, expires_at, how_to_use, and a verifiable spend receipt after confirmed settlement. Never activates without a verified transfer. When to use: call day_pass_activate when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `x_payment` (string): Base64 JSON x402 payment envelope signed from the live challenge, sent as X-Payment.

Output parameters:

- `access_key` (string)
- `activated` (boolean)
- `already_active` (boolean)
- `expires_at` (string)
- `how_to_use` (object)
- `x711_credits` (number)

### `capability_search` (~195 tokens)

Search across all 100+ Zambo Stack tools via one MCP connection to find what fits your use case. Returns up to 8 relevant products with relevance scores, descriptions, taglines, and callable API endpoints. Use this before zambo_universal when you know exactly which product you want. When to use: call capability_search when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input parameters:

- `keyword` (string): Natural-language alias for q.
- `q` (string): Search keyword or phrase. Also accepts the natural aliases query, keyword, or search. Example: 'code audit', 'prompt injection defense', 'wallet scoring', 'lead generation', 'trust verification'
- `query` (string): Alias for q. Use q when possible.
- `search` (string): Natural-language alias for q.

Output parameters:

- `count` (number)
- `matched` (array)
- `tools` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/zambodotdev-zambo/api-mcp#diagnostics

## Score history

- 2026-09-20: 73
- 2026-09-19: 71
- 2026-09-18: 71
- 2026-09-17: 70
- 2026-09-16: 70
- 2026-09-15: 69
- 2026-09-14: 76
- 2026-09-13: 75
- 2026-09-12: 72
- 2026-09-11: 71

## Common questions

### What is the Zambo MCP server?

Zambo is an MCP server listed in the public MCP registry as io.github.zambodotdev/zambo. Give your AI hands. One URL. Type a job. Get a receipt. This page covers its hosted endpoint (https://zambo.dev/api/mcp).

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

Zambo scores 73 out of 100 on VerifyMCP. 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 Zambo MCP server expose?

Zambo exposes 11 tools: zambo_universal, live_price, leadsignal, provibe_audit, ghost_audit_site, and 6 more. Their descriptions and schemas cost roughly 2,692 tokens of context every time the server is loaded.

### Does the Zambo MCP server require authentication?

No. We connected to Zambo without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Zambo MCP server still maintained?

Zambo 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.

## Links

- Remote endpoint: https://zambo.dev/api/mcp
- Repository: https://github.com/zambodotdev/zambo-mcp
- Website: https://zambo.dev/
- Changelog RSS feed: https://verifymcp.io/servers/zambodotdev-zambo/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/zambodotdev-zambo/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/zambodotdev-zambo/api-mcp