Grounded Docs is an MCP server that builds a local, version-aware index of documentation from websites, code repositories, package registries, local files, and archives for AI coding assistants. It helps assistants retrieve current project-specific documentation and supports MCP-compatible clients such as Claude, Cline, and similar tools. The catalogue add-ons provide skills, commands, and instructions for working with this documentation server.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add arabold/docs-mcp-server --skill docs-searchgit clone --depth 1 https://github.com/arabold/docs-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arabold/docs-mcp-server/docs-search)<a href="https://agentmods.dev/skills/arabold/docs-mcp-server/docs-search"><img src="https://agentmods.dev/badge/skills/arabold/docs-mcp-server/docs-search/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arabold/docs-mcp-server/docs-search"><img src="https://agentmods.dev/badge/skills/arabold/docs-mcp-server/docs-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 9 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 37 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 64 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 81 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 91 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 105 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 124 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 127 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01212 |
| Opus 5.5 | $0.00021 | $0.00485 |
| Sonnet 5.5 | $0.00010 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
docs-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Search
Search the local Grounded Docs index for library documentation. These commands print JSON by default and never change the index.
When to use
- You need to answer a question about a library's API or behavior.
- You want to check which libraries and versions are indexed.
- You need the indexed version that best matches a version constraint.
Run list first if you are unsure whether a library is indexed. If it is not,
use the docs-manage skill to index it before searching.
Commands
All three commands accept these flags:
| Flag | Description |
|---|---|
--output json|yaml|toon |
Output format (default: JSON) |
--server-url <url> |
Use a remote worker (e.g. http://localhost:8080/api) instead of the local store |
--quiet |
Log errors only |
--verbose |
Log debug output |
list
List every indexed library and its versions.
npx @arabold/docs-mcp-server@latest list --output yaml
Example output:
- name: react
versions:
- id: 1
version: 19.0.0
documentCount: 412
uniqueUrlCount: 198
indexedAt: 2026-10-18T22:28:47.000Z
status: completed
sourceUrl: https://react.dev/reference/react
preserveHashes: false
An empty version is the library's unversioned documentation. A version with
status: completed is fully indexed. Other statuses (queued, running,
updating, failed, cancelled, not_indexed) mean the content may be
missing or incomplete, and such a version may carry a progress field. An
empty index prints [].
search
Search an indexed library with a natural-language query.
npx @arabold/docs-mcp-server@latest search <library> "<query>" [options]
| Flag | Alias | Default | Description |
|---|---|---|---|
--version <ver> |
-v |
newest version | Exact version or range (e.g. 18.x, 5.2.x). An exact version also matches the closest older version. |
--limit <n> |
-l |
5 |
Maximum number of results (1 to 100) |
--exact-match |
-e |
false |
Match only the exact --version, without falling back to an older one. Requires --version. |
--embedding-model <model> |
Embedding model, e.g. openai:text-embedding-3-small |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +14 lines · -2 tokens per session 57e2e0de8b45
- 1mo ago First seen · 131 lines · 54 tokens per session scan A 796cfe10322b
docs-search is a skill published in the GitHub repository arabold/docs-mcp-server (1,817 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,212 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
command-parity-router
Auto-route natural-language requests to existing ai-kb command workflows with full command parity and multi-workflow composition. Use by default when user does not explicitly call a slash command.
d3-viz
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke…
tailwind-design-system
Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.
gsap-plugins
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG…
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
music-to-video
Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography…