# AILANG Docs (remote · mcp.ailang.sunholo.com)

AILANG language reference, stdlib, examples and benchmarks for agents that write AILANG.

- Trust score: 72/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.ailang.sunholo.com`: 72/100 (this document), [markdown](https://verifymcp.io/servers/sunholo-data-ailang-docs/mcp.md), [page](https://verifymcp.io/servers/sunholo-data-ailang-docs/mcp)

## Channel facts

- Endpoint: `https://mcp.ailang.sunholo.com/mcp/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.60.6`

## 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 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1404 tokens (~61/item across 23 items; 22 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability check failed: schema churn in the 9 days we've observed: 1 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 73/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 20% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 23 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 AILANG Docs MCP server?

AILANG Docs is a hosted endpoint at https://mcp.ailang.sunholo.com/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 sunholo-data-ailang-docs 'https://mcp.ailang.sunholo.com/mcp/'
```

### Cursor

```json
{
  "mcpServers": {
    "sunholo-data-ailang-docs": {
      "url": "https://mcp.ailang.sunholo.com/mcp/"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sunholo-data-ailang-docs": {
      "type": "http",
      "url": "https://mcp.ailang.sunholo.com/mcp/"
    }
  }
}
```

### Codex

```toml
[mcp_servers.sunholo-data-ailang-docs]
url = "https://mcp.ailang.sunholo.com/mcp/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sunholo-data-ailang-docs": {
      "type": "remote",
      "url": "https://mcp.ailang.sunholo.com/mcp/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sunholo-data-ailang-docs --url 'https://mcp.ailang.sunholo.com/mcp/' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sunholo-data-ailang-docs:
    url: "https://mcp.ailang.sunholo.com/mcp/"
```

### Netclaw

```json
{
  "McpServers": {
    "sunholo-data-ailang-docs": {
      "Transport": "http",
      "Url": "https://mcp.ailang.sunholo.com/mcp/"
    }
  }
}
```

### Vellum

```bash
assistant mcp add sunholo-data-ailang-docs -t streamable-http -u 'https://mcp.ailang.sunholo.com/mcp/'
```

### Other

```json
{
  "mcpServers": {
    "sunholo-data-ailang-docs": {
      "type": "http",
      "url": "https://mcp.ailang.sunholo.com/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.

### 2026-11-19 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17.

### 2026-11-18 (score 71, 0)

- [functional] Server version: 0.60.5 → 0.60.6

### 2026-11-17 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10.

### 2026-11-16 (score 70, 0)

- [security regression] Stability: 0.10 → fail
- [security regression] Tool “benchmark_run” was removed
- [security] Tool “benchmarks_compare” rewrote its description, which is the text the model reads
- [security] Tool “design_doc” rewrote its description, which is the text the model reads
- [security] Tool “example_get” rewrote its description, which is the text the model reads
- [security] Tool “examples_list” rewrote its description, which is the text the model reads
- [security] Tool “prompt_get” rewrote its description, which is the text the model reads
- [security] Tool “roadmap” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 55 → 61
- [functional regression] “benchmarks_compare” dropped the required parameter “version”
- [functional] Server version: 0.60.4 → 0.60.5

### 2026-11-14 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 69, 0)

- [security] Tool “docs_nav” rewrote its description, which is the text the model reads
- [security] Tool “docs_search” rewrote its description, which is the text the model reads
- [security] Tool “onboarding_guide” rewrote its description, which is the text the model reads
- [security] Tool “submit_feedback” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional] Destructive annotations: pass → 100
- [functional] Server version: 0.60.2 → 0.60.4
- [cosmetic] “submit_feedback” reworded the description of “auto_dispatch”
- [cosmetic] “submit_feedback” reworded the description of “contact”
- [cosmetic] “submit_feedback” reworded the description of “package”

### 2026-11-12 (score 69)

First indexed and scored.

## MCP tools (22)

### `ailang_versions` (~21 tokens)

AILANG versions

List all AILANG versions the server can answer for.

### `benchmarks_compare` (~57 tokens)

Compare two models on benchmarks

Two models side by side across every banked run: passes, runs, pass rate,
cost and failures by category. Model names are as benchmarks_list gives them.

Input parameters:

- `modelA` (string, required)
- `modelB` (string, required)

### `benchmarks_for_model` (~52 tokens)

Benchmarks for a model

Where does a given model pass/fail? Optional version filter.
Output: {passes: [...], fails_by_category: {...}, total_cost}

Input parameters:

- `model` (string, required)
- `version` (string, required)

### `benchmarks_list` (~30 tokens)

List benchmark runs

List benchmark suites and runs, optionally filtered to a since_version cutoff.

Input parameters:

- `sinceVersion` (string, required)

### `changelog_for_version` (~33 tokens)

Changelog for a version

What changed in a given release (added/changed/fixed/breaking).

Input parameters:

- `version` (string, required)

### `design_doc` (~56 tokens)

Read a design doc

Full design doc by slug (e.g. "m-agent-mcp-website"), as markdown. Long
documents are cut at 30,000 characters and say so; url opens the whole one.

Input parameters:

- `slug` (string, required)

### `design_docs_list` (~57 tokens)

List design docs

List planned/implemented/rejected design docs, optionally filtered by version.
state = "planned" | "implemented" | "rejected" | ""; empty = all.

Input parameters:

- `state` (string, required)
- `version` (string, required)

### `docs_nav` (~40 tokens)

Docs navigation

The AILANG docs site's navigation tree for a version, as JSON: section and
page titles with their paths.

Input parameters:

- `forVersion` (string, required)

### `docs_search` (~81 tokens)

Search AILANG docs

Full-text search of the AILANG documentation for a version (case-insensitive,
on page titles and text). Returns the top 10 matches, docs pages before
archived teaching prompts, each with its path, title, first 10 headings and
an excerpt around the match.

Input parameters:

- `forVersion` (string, required)
- `query` (string, required)

### `effects_catalog` (~29 tokens)

Effects catalog

All declared effects with capability mapping and the version they appeared in.

Input parameters:

- `forVersion` (string, required)

### `example_for_concept` (~57 tokens)

Example for a concept

Best-fit examples for a free-form concept query ("how do I use effects?").
Filters server-side on why + title; returns up to 5 matches.

Input parameters:

- `concept` (string, required)
- `forVersion` (string, required)

### `example_get` (~60 tokens)

Get an example

Full source of one example by path (as examples_list gives it, e.g.
"runnable/hello.ail"; a leading "examples/" is accepted), at the release.

Input parameters:

- `forVersion` (string, required)
- `path` (string, required)

### `examples_list` (~110 tokens)

List examples

Examples in the release's manifest (examples/manifest.json at its tag).
features = comma-separated tags ("effects,records"); empty = no filter.
status = "working" | "broken" | "aspirational" | "" ("passing" = working,
"failing" = the other two); empty = working only. At most 50 are returned;
total says how many matched.

Input parameters:

- `features` (string, required)
- `forVersion` (string, required)
- `status` (string, required)

### `install_guide` (~105 tokens)

AILANG install guide

Harness-aware install instructions for AILANG.
harness: "claude-code" | "gemini-cli" | "codex-cli" | "manual" | "build-from-source" | ""
platform: only meaningful for "manual" (e.g. "darwin-arm64", "linux-amd64"); ignored otherwise
Empty harness returns ALL harnesses + the remote_mcp config block.

Input parameters:

- `harness` (string, required)
- `platform` (string, required)

### `limitations_list` (~38 tokens)

Known limitations

Known limitations (Y-combinator, etc.) optionally filtered by category.

Input parameters:

- `category` (string, required)
- `forVersion` (string, required)

### `onboarding_guide` (~72 tokens)

AILANG onboarding guide

Step-by-step guide to getting started with AILANG, for an AI coding agent
and for a human developer. role: "agent" | "developer" | "" (both). The
guide for both roles is returned whatever role says; pick the part you need.

Input parameters:

- `role` (string, required)

### `prompt_get` (~49 tokens)

Get an AILANG teaching prompt

Fetch the canonical teaching prompt for a version.
kind = "" (the full prompt) | "agent" | "devtools".

Input parameters:

- `forVersion` (string, required)
- `kind` (string, required)

### `roadmap` (~37 tokens)

AILANG roadmap

What's shipping next, what's been rejected and why: the roadmap page of the
AILANG site, generated from the planned design docs, as markdown.

### `stdlib_module` (~34 tokens)

Stdlib module reference

Full module: exports + signatures + docstrings.

Input parameters:

- `forVersion` (string, required)
- `name` (string, required)

### `stdlib_modules` (~33 tokens)

List stdlib modules

List stdlib modules available in this AILANG version with one-line summaries.

Input parameters:

- `forVersion` (string, required)

### `stdlib_search` (~51 tokens)

Search the stdlib

Find stdlib functions by name, signature, or keyword.
Filters the pre-built search index server-side; returns top 20 matches.

Input parameters:

- `forVersion` (string, required)
- `query` (string, required)

### `submit_feedback` (~283 tokens)

Send feedback

Send a bug report, feature request, documentation gap or limitation about AILANG to the AILANG team. Use it only when the user asks to report something, and leave out personal or confidential information. Categories: bug, feature, docs, limitation. Body up to 10 KB, snippet up to 4 KB. `contact` is optional, for a reply. `package` (vendor/name) sends the report to that AILANG package's maintainers instead. Returns a ticket ID.

Input parameters:

- `ailang_version` (string, required): The reporter's CLI version (free-form, used for triage)
- `auto_dispatch` (boolean): Let the package maintainers' automation act on the report before a person reads it. Only if the user asks. Default false: a person triages it first.
- `body` (string, required): Full description (≤10 KB)
- `category` (string, required): bug | feature | docs | limitation
- `contact` (string): Optional address for a reply. Only if the user gives one
- `package` (string): Optional vendor/name (e.g. "sunholo/auth") to send the report to that package's maintainers. Empty = the AILANG team.
- `snippet` (string): Optional code/error snippet (≤4 KB)
- `title` (string, required): Short title for the report

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/sunholo-data-ailang-docs/mcp#diagnostics

## Score history

- 2026-11-21: 72
- 2026-11-20: 72
- 2026-11-19: 72
- 2026-11-18: 71
- 2026-11-17: 71
- 2026-11-16: 70
- 2026-11-15: 70
- 2026-11-14: 70
- 2026-11-13: 69
- 2026-11-12: 69

## Common questions

### What is the AILANG Docs MCP server?

AILANG Docs is an MCP server listed in the public MCP registry as io.github.sunholo-data/ailang-docs. AILANG language reference, stdlib, examples and benchmarks for agents that write AILANG. This page covers its hosted endpoint (https://mcp.ailang.sunholo.com/mcp/).

### Is the AILANG Docs MCP server safe to use?

AILANG Docs scores 72 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 AILANG Docs MCP server expose?

AILANG Docs exposes 22 tools: ailang_versions, benchmarks_compare, benchmarks_for_model, benchmarks_list, changelog_for_version, and 17 more. Their descriptions and schemas cost roughly 1,385 tokens of context every time the server is loaded.

### Does the AILANG Docs MCP server require authentication?

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

### Is the AILANG Docs MCP server still maintained?

AILANG Docs is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the AILANG Docs MCP server?

VerifyMCP ran 13 checks on AILANG Docs, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.ailang.sunholo.com/mcp/
- Repository: https://github.com/sunholo-data/ailang
- Website: https://ailang.sunholo.com/
- Changelog RSS feed: https://verifymcp.io/servers/sunholo-data-ailang-docs/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sunholo-data-ailang-docs/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/sunholo-data-ailang-docs/mcp.json
- HTML version of this page: https://verifymcp.io/servers/sunholo-data-ailang-docs/mcp
