# Citable (npm · citable-mcp)

SEO and AI-visibility checks agents buy per call — USDC on Solana, no API key.

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `citable-mcp`: 75/100 (this document), [markdown](https://verifymcp.io/servers/zaialamm-citable-mcp/citable-mcp.md), [page](https://verifymcp.io/servers/zaialamm-citable-mcp/citable-mcp)

## Channel facts

- Registry: `npm`
- Package: `citable-mcp`
- Version: `0.6.3`
- 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 2026-09-20.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 150 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 18 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3012 tokens (~158/item across 19 items; 19 tools + 0 resources), over budget; trim descriptions and params.
  - 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**: 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 20 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 Citable MCP server?

Citable runs locally as an npm package, launched with npx -y citable-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 zaialamm-citable-mcp -- npx -y citable-mcp
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add zaialamm-citable-mcp -- npx -y citable-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add zaialamm-citable-mcp --command npx --arg -y --arg citable-mcp
```

### Hermes

```yaml
mcp_servers:
  zaialamm-citable-mcp:
    command: "npx"
    args: ["-y", "citable-mcp"]
```

### Netclaw

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

### Vellum

```bash
assistant mcp add zaialamm-citable-mcp -t stdio -c npx -a -y citable-mcp
```

### Other

```json
{
  "mcpServers": {
    "zaialamm-citable-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "citable-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.

### 2026-09-19 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 73, +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.

### 2026-09-13 (score 72, +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.

### 2026-09-11 (score 71, +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.

### 2026-09-09 (score 70, +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.

### 2026-09-06 (score 69, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-30 (score 65, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (19)

### `citable_prices` (~79 tokens)

Citable — endpoints and prices

Free. Lists Citable's SEO endpoints with current per-call USDC prices, plus the wallet that pays: address (the one to fund), walletMode (keypair or sign-in), balanceUsdc and funded. When it is empty, `setup` gives the two ways to fund it — put them to the user. Call this first.

### `citable_connect` (~166 tokens)

Citable — connect a sign-in wallet (no crypto needed)

Free. For people who do not use crypto. Returns a link to open in a browser: sign in at Citable with Google or email, add a few dollars of USDC, click Connect — the agent then pays from that wallet. The link works for 15 minutes; when the user says it is done, call citable_prices to confirm (walletMode becomes sign-in). {status:true} only reports; {reset:true} disconnects and returns to the keypair. The first connect installs Para's SDK under ~/.config/citable/para (about 200 MB, once).

Input parameters:

- `reset` (boolean): Forget the sign-in session and pay from the keypair again
- `status` (boolean): Only report the current state; do not start a new connection

### `citable_keyword_suggest` (~211 tokens)

Citable — keyword suggestions

Paid ($0.005 USDC per call). Expands a seed keyword into autocomplete suggestions, related queries and questions, deduped and ranked across Google, YouTube and Bing. Returns `suggestions[]` and `questions[]` with a 0–1 prominence score, the sources each came from, and whether the keyword still contains the seed.

Input parameters:

- `country` (string): Country code (default us)
- `depth` (integer): 0 seed only · 1 + questions/modifiers · 2 (default) + a–z sweep
- `lang` (string): Language code (default en)
- `limit` (integer): Max keywords per list (default 100)
- `seed` (string, required): Seed keyword — a topic or phrase people type, e.g. 'solana rpc'. Not a domain: for the keywords a site ranks for use citable_domain_keywords
- `sources` (string): Comma list of google,youtube,bing (default all)

### `citable_onpage_audit` (~138 tokens)

Citable — on-page SEO audit

Paid ($0.01 USDC per call). Fetches one URL and returns a scored on-page audit: title, meta description, canonical, robots, viewport, lang, heading counts and text, word count, internal/external links, image alt coverage, Open Graph, JSON-LD types, HTTP details, and 15 weighted checks with a 0–100 score. Not charged if the page cannot be fetched.

Input parameters:

- `url` (string, required): Absolute http(s) URL of one page to audit — not a bare domain; for a domain-level view use citable_domain_overview or citable_citability_report

### `citable_ai_visibility` (~208 tokens)

Citable — AI-visibility check

Paid ($0.05 USDC per engine asked; $0.20 for all four). Asks the AI answer engines (Perplexity, Gemini, OpenAI, Claude — whichever the deployment has configured) a prompt through their official APIs and reports which ones cite the domain: `mentioned`, 1-based `position` in each engine's citation list, and the full cited-domain list per engine. One run per engine — answers vary between runs, so call 2–3 times for signal. Not charged if no engine answers.

Input parameters:

- `domain` (string, required): Hostname to look for in the citations, e.g. example.com
- `engines` (string): Comma list of perplexity,gemini,openai,anthropic (default: all configured)
- `prompt` (string, required): The question a buyer would ask, supplied by the user — never invented (citable_cited_prompts returns observed ones), e.g. 'best solana rpc provider'

### `citable_rank_check` (~145 tokens)

Citable — Google rank check

Paid ($0.012 USDC per call). Google organic position of a domain for a keyword via a licensed SERP feed: 1-based `position` (null if outside the checked window), the ranking URL and title, plus the top-10 result list. Not charged if the feed is unavailable.

Input parameters:

- `domain` (string, required): Hostname to find, e.g. example.com
- `gl` (string): Country code (default us)
- `hl` (string): Language code (default en)
- `keyword` (string, required): Search query, e.g. 'solana rpc'
- `num` (integer): Results window to check (default 20)

### `citable_keyword_research` (~162 tokens)

Citable — everything about one keyword, in one call

Paid ($0.06 USDC per call). One seed returns keywords AND questions, merged from public autocomplete and the paid keyword index, with search volume, CPC, difficulty and intent attached. Each row says which sources found it — both is the strongest signal. Cheaper than citable_keyword_ideas plus citable_keyword_metrics separately; reach for those only when you want to control exactly what you pay for. Not charged on failure.

Input parameters:

- `country` (string): Country code (default us)
- `lang` (string): Language code (default en)
- `limit` (integer): Rows per list (default 100)
- `seed` (string, required): Keyword to research — a topic, not a domain, e.g. 'reksadana'

### `citable_keyword_ideas` (~160 tokens)

Citable — keyword research from a seed

Paid ($0.05 USDC per call). Keyword research: one seed returns up to 100 keywords that contain it, each with search volume, CPC, competition, difficulty and intent, ordered by volume. Full-text matched, so results stay on topic. Use citable_keyword_suggest for the exact phrasings people type (no volume), and citable_keyword_metrics when you already have a shortlist. Not charged on failure.

Input parameters:

- `country` (string): Country code (default us)
- `lang` (string): Language code (default en)
- `limit` (integer): Ideas to return (default 50)
- `seed` (string, required): Keyword to research — a topic, not a domain, e.g. 'seo api'

### `citable_keyword_metrics` (~140 tokens)

Citable — keyword volume & difficulty

Paid ($0.03 USDC per call, covers the whole batch). Search volume, CPC, competition, keyword difficulty and search intent for 1–20 keywords — licensed clickstream-derived estimates. Answers in request order; unknown keywords return null metrics. Pair with citable_keyword_suggest: expand a seed there, price the shortlist here. Not charged if the metrics feed is unavailable.

Input parameters:

- `country` (string): Country code (default us)
- `keywords` (string, required): Comma list of 1–20 keywords, e.g. 'solana rpc,best launchpad'
- `lang` (string): Language code (default en)

### `citable_top_cited_pages` (~111 tokens)

Citable — top AI-cited pages of a domain

Paid ($0.22 USDC per call). Which pages of a domain AI engines cite most, from an aggregated index of AI answers — per-page mentions, AI search volume, per-engine and per-language splits, plus domain totals. Answers 'what already works on this site — write more of that'. Not charged if the index is unavailable.

Input parameters:

- `domain` (string, required): Domain to inventory, e.g. example.com
- `limit` (integer): Pages to return (default 10)

### `citable_citability_report` (~137 tokens)

Citable — full citability report (bundle)

Paid ($0.30 USDC per call; $0.43 bought separately). One call bundles the on-page citability audit, AI visibility across all configured engines, and the domain's top AI-cited pages. Answers: can AI read this site, who cites it today, and which pages already work. Not charged on failure.

Input parameters:

- `domain` (string, required): Domain to report on, e.g. example.com
- `limit` (integer): Top cited pages to include (default 10)
- `prompt` (string, required): REQUIRED: the buyer question to ask the engines — supplied by the user, never invented

### `citable_cited_prompts` (~172 tokens)

Citable — prompts a domain is already cited for

Paid ($0.25 USDC per call). The real questions AI answer engines cite a domain for, from an aggregated index of AI answers — question, answer snippet, AI search volume, and the exact URL cited. These are observed prompts, never generated ones, so use this to discover what to track instead of inventing them. Repeated observations of one question are collapsed, with `observations` counting them. Point it at a competitor's domain to get the prompts they win and you do not. Not charged on failure.

Input parameters:

- `domain` (string, required): Domain to look up, e.g. example.com — or a competitor's
- `limit` (integer): Prompts to return (default 10)
- `platform` (string): Restrict to one engine (default: both)

### `citable_ai_mentions_trend` (~146 tokens)

Citable — monthly AI-mention trend for a domain

Paid ($0.18 USDC per call). Stateless prompt tracking: monthly AI mentions and AI search volume for a domain with month-over-month deltas and a direction summary. No tracker to create and nothing to poll — one call returns the whole series. The index starts 2025-08-01. Not charged on failure.

Input parameters:

- `domain` (string, required): Domain to track, e.g. example.com
- `from` (string): Start date yyyy-mm-dd (clamped to 2025-08-01)
- `platform` (string): Restrict to one engine (default: both)
- `to` (string): End date yyyy-mm-dd

### `citable_ai_share_of_voice` (~128 tokens)

Citable — AI share of voice across a competitive set

Paid ($0.18 USDC per call, whatever the set size). Compare 2–10 domains inside the AI-answer index: mentions, AI search volume, and each domain's share of the compared set, with per-engine and per-language splits. Share is of the set you asked about, not of the whole index. Not charged on failure.

Input parameters:

- `domains` (string, required): Comma list of 2–10 hostnames, e.g. you.com,rival.com,other.com
- `platform` (string): Restrict to one engine (default: both)

### `citable_domain_overview` (~121 tokens)

Citable — domain organic footprint

Paid ($0.03 USDC per call). One domain's organic footprint from a ranking index: keywords ranked, top-3/top-10 counts, estimated monthly traffic and its ad value, plus the paid-search side. The first call for any domain question; then citable_domain_keywords for what it ranks for. Not charged on failure.

Input parameters:

- `country` (string): Country code (default us)
- `domain` (string, required): Hostname to profile, e.g. example.com
- `lang` (string): Language code (default en)

### `citable_domain_keywords` (~138 tokens)

Citable — the keywords a domain ranks for

Paid ($0.04 USDC per call). The keywords a domain actually ranks for — volume, CPC, position, month-over-month movement (previousPosition, change, status) and the ranking URL, highest volume first, with the index's total count. Point it at a competitor for their playbook. Not charged on failure.

Input parameters:

- `country` (string): Country code (default us)
- `domain` (string, required): Hostname to inventory, e.g. example.com — a competitor's works too
- `lang` (string): Language code (default en)
- `limit` (integer): Keywords to return (default 25)

### `citable_domain_history` (~184 tokens)

Citable — a domain's footprint month by month

Paid ($0.03 USDC per call). How a domain's organic footprint has moved, month by month (up to `months`; the current month may be partial), from the ranking index: keywords ranked, top-10 count, estimated traffic and value, and how many keywords were new, up, down or lost each month, plus a first-to-last trend. The stateless way to track rankings — nothing is stored, the index keeps the history. Monthly resolution; for one keyword's position today use citable_rank_check. Not charged on failure.

Input parameters:

- `country` (string): Country code (default us)
- `domain` (string, required): Hostname to track, e.g. example.com
- `lang` (string): Language code (default en)
- `months` (integer): Calendar months of history, 2–24 (default 12)

### `citable_serp` (~122 tokens)

Citable — raw Google results page

Paid ($0.008 USDC per call). The raw Google results page for a keyword: organic results with snippets, plus People-Also-Ask questions and related searches when present. rank-check answers where am I; this answers what the page looks like. Not charged on failure.

Input parameters:

- `gl` (string): Country code (default us)
- `hl` (string): Language code (default en)
- `keyword` (string, required): Search query — a phrase people type, not a domain
- `num` (integer): Results depth (default 10)

### `citable_backlinks` (~99 tokens)

Citable — backlink profile and top referring domains

Paid ($0.10 USDC per call). Link profile in one call: total backlinks, referring domains, domain rank, broken links and nofollow share, plus the top referring domains with first-seen dates. The link-prospecting starting point. Not charged on failure.

Input parameters:

- `domain` (string, required): Hostname to profile, e.g. example.com
- `limit` (integer): Referring domains to return (default 10)

## Diagnostics

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

## Score history

- 2026-09-20: 75
- 2026-09-19: 75
- 2026-09-18: 74
- 2026-09-17: 74
- 2026-09-16: 73
- 2026-09-15: 73
- 2026-09-14: 72
- 2026-09-13: 72
- 2026-09-12: 71
- 2026-09-11: 71
- 2026-09-10: 70
- 2026-09-09: 70
- 2026-09-08: 69
- 2026-09-07: 69
- 2026-09-06: 69
- 2026-09-05: 65
- 2026-09-04: 65
- 2026-09-03: 65
- 2026-09-02: 65
- 2026-09-01: 65
- 2026-08-31: 65
- 2026-08-30: 65
- 2026-08-29: 50

## Common questions

### What is the Citable MCP server?

Citable is an MCP server listed in the public MCP registry as io.github.zaialamm/citable-mcp. SEO and AI-visibility checks agents buy per call, USDC on Solana, no API key. This page covers its npm package (citable-mcp).

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

Citable scores 75 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 Citable MCP server expose?

Citable exposes 19 tools: citable_prices, citable_connect, citable_keyword_suggest, citable_onpage_audit, citable_ai_visibility, and 14 more. Their descriptions and schemas cost roughly 2,767 tokens of context every time the server is loaded.

### Is the Citable MCP server still maintained?

Citable 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 Citable MCP server under?

Citable 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/citable-mcp
- Socket report: https://socket.dev/npm/package/citable-mcp
- Website: https://citable.run/
- Changelog RSS feed: https://verifymcp.io/servers/zaialamm-citable-mcp/citable-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/zaialamm-citable-mcp/citable-mcp.json
- HTML version of this page: https://verifymcp.io/servers/zaialamm-citable-mcp/citable-mcp