# iLang

> iLang is an open-source MCP server for ai models and llm tooling. Runtime for iLang, a text protocol AIs use to pass intent between each other. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** API, CLI
- **Website:** https://ilang.ai
- **Repository:** https://github.com/ilang-ai/ilang.ai/tree/HEAD/functions
- **MCP Registry name:** ai.ilang/mcp
- **Categories:** AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

Rather than a data service, this server hands an AI the iLang protocol itself. The registry entry says it can load the protocol, validate iLang text, look up verbs, and serve the SOUL and Source Book documents.

iLang is described as a pure-text protocol with two syntaxes, 88 verbs and 29 core modifiers, released as version 5.0 under the MIT license. Messages carry intent, authority, a done-when condition, evidence and an action score, and a grammar validator lets both ends check the same rules.

The site says it has been tried across seven models, and that irreversible actions are left to a human. The site also offers copy-paste use in chat and pip and npm loader packages.

## Features

- **Protocol loading:** Gives an AI the current iLang runtime text to read as instructions.
- **Text validation:** Checks iLang text against the shared grammar.
- **Verb lookup:** Looks up the verbs of the 88-verb vocabulary.
- **Reference documents:** Serves SOUL and Source Book documents named in the registry entry.
- **Model-agnostic:** Described as working with any model that has enough context.

## Good for

- Load iLang into an assistant without pasting it
- Validate a hand-written iLang message
- Look up a verb while drafting a protocol message
- Pass work between two AIs with a stated done-when condition

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http mcp https://mcp.ilang.ai/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.ilang.ai/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.ilang.ai/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.ilang.ai/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.ilang.ai/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.ilang.ai/mcp"
    }
  }
}
```

## Tools

- `ilang_runtime`: iLang is a specification between humans and AI: before the AI acts, it defines what that action is authorized to become; after, code checks whether it was done right. Return the official iLang runtime, the working text of the specification (about 18,600 tokens), verified against the canon's sha256. Load it once per conversation, then use iLang internally. media=true adds the image, video and audio
- `ilang_runtime_lite`: Return iLang runtime lite: the two syntaxes, the verb table (88 verbs with their 13 Greek aliases), the 29 modifiers, the error codes, the declaration body forms, the registry of 32 declarations and the entity registry (25 entities), taken word for word from the canon's full runtime and checked against its sha256. About 18,000 characters, where ilang_runtime returns about 93,000. Enough to write i
- `ilang_full`: Return a section of the full specification that the core runtime leaves out, found by its heading (for example "Declaration Grammar" or "Boundary Cases"), or the whole full text when no heading is given.
- `ilang_validate`: Check iLang text with the canon grammar and registry validator. Returns error, warning and info counts and each finding with its line, code and message. An E302 finding (unknown modifier) may also carry did_you_mean, the registered modifier this server suggests for the key; the suggestion is added here and is not part of the canon validator's output.
- `ilang_lookup`: [GET:@DICT|whr=q=term]=>[Ω] Look up an iLang verb, modifier, entity or declaration by name, alias or meaning. Returns type, name, alias, category, meaning, values and source_url. not_found=true when nothing matches; never invent terms.
- `ilang_faq`: [GET:@FAQ|whr=q=question]=>[Ω] Return the published ilang.ai FAQ entries closest to a question about the protocol (what it is, MCP/A2A comparison, prompt compression, versions, judgment layer, SOUL, the Source Book). Includes source_url.
- `ilang_soul`: [GET:@SOUL|whr=form]=>[Ω] Return SOUL 2.0, the published iLang document that sets how an AI behaves by default: a judgment layer for its default persona. The text comes back as the file on ilang.ai/soul/ (about 2,000 characters), followed by a JSON line with version, date, license, DOI, file url and the sha256 of the text served. Paste the text where the AI reads its instructions. form=iml returns
- `ilang_source_book`: [GET:@SOURCE_BOOK|whr=form]=>[Ω] Return Source Book 2.9, the engineering book every iLang engineering book is anchored to: pasted into an agent app that has a shell, files and the web, and given a tutorial, the agent confirms the tutorial's numbers against official sources and writes BOOK.md, an English iLang book any agent can carry out. The text comes back as the file on ilang.ai/source-book/ (a
- `ilang_book_check`: [CHEK:@BOOK|whr=rubric_A1_A2]=>[Ω] Run the Source Book's two code checks on an engineering book: A1, the text opens and closes with the ::ILANG::v5.0::ENGINEERING_BOOK marker (exactly two such lines), and A2, the canon grammar validator reports zero errors and zero warnings (strict). Returns pass or fail per item with the validator's findings. For an agent that has no shell to run ilang_grammar_va

## FAQ

### What license is iLang under?

The site's definition lists MIT.

### Which models has it been tried with?

The site lists ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM.

### Is there an install path besides the server?

The site mentions pip install ilang-protocol and npm install ilang-protocol loaders, or pasting the text into a chat.

### Is iLang free?

Yes. iLang is open source, so you can use and self-host it for free.

### How do I add iLang to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.ilang.ai/mcp

### What are the best alternatives to iLang?

The closest alternatives to iLang are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

## Alternatives

- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [signafAIde](https://ai-powered.com/mcp/signafaide): signafAIde is a freemium MCP server for security.
- [Toolkien](https://ai-powered.com/mcp/toolkien): Toolkien is an open-source MCP server for ai models and llm tooling.
- [Lugh](https://ai-powered.com/mcp/lugh): Lugh is an open-source MCP server for ai models and llm tooling.
- [HypePaper](https://ai-powered.com/mcp/hypepaper): HypePaper is a freemium MCP server for ai models and llm tooling.
- [Agent Data Tools: Compact (find, describe, run)](https://ai-powered.com/mcp/agent-data-tools-compact-find-describe-run): Agent Data Tools: Compact (find, describe, run) is a freemium MCP server for developer tools.
- [Angel Agent Guard: pre-purchase check + prompt-injection scan](https://ai-powered.com/mcp/angel-agent-guard-pre-purchase-check-prompt-injection-scan): Angel Agent Guard: pre-purchase check + prompt-injection scan is a freemium MCP server for ai models and llm tooling.
- [Mizan Calibration](https://ai-powered.com/mcp/mizan-calibration): Mizan Calibration is a free MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/ilang
