iLang
● Activeai.ilang/mcp
iLang runtime for any AI: load the protocol, validate iLang text, look up verbs, SOUL, Source Book.
Connect this server
One click to install, or copy the config below. Suits: Cursor · HTTP clients.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"mcp": {
"url": "https://mcp.ilang.ai/mcp"
}
}
}claude mcp add --transport http mcp https://mcp.ilang.ai/mcpcode --add-mcp '{"name":"mcp","type":"http","url":"https://mcp.ilang.ai/mcp"}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Other
- Version
- 2.3.0
- Registry
- active
- Published
- 11/13/2026
Live check
checked Nov 19, 2026, 01:07 UTCThe endpoint answered the MCP handshake as "iLang" and listed 9 tools. Answering since Nov 17, 2026.
Context cost ≈ 1.6k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 9 tools.
Tools (9)
tool list changed Nov 19, 2026, 01:07 UTCilang_runtime1 paramiLang 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 extension (about 18,000 tokens more).
Show parametersHide parameters
mediabooleanAdd the media extension
ilang_runtime_liteReturn 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 iLang and check it with ilang_validate; it leaves out the execution and judgment layers, so load ilang_runtime when a task needs them.
ilang_full1 paramReturn 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.
Show parametersHide parameters
sectionstringA heading, or part of one
ilang_validate1 paramCheck 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.
Show parametersHide parameters
textstringrequirediLang, or Markdown that carries iLang blocks
ilang_lookup1 param[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.
Show parametersHide parameters
qstringrequiredTerm, alias or keyword, e.g. XLAT, lng, @PREV, BUDGET
ilang_faq1 param[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.
Show parametersHide parameters
qstringrequired
ilang_soul1 param[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 the IML 0.5 form instead.
Show parametersHide parameters
formstringilang (default) or iml
ilang_source_book1 param[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/ (about 7,600 characters), followed by a JSON line with version, date, license, DOI, file url and the sha256 of the text served. form=iml returns the IML 0.5 form instead.
Show parametersHide parameters
formstringilang (default) or iml
ilang_book_check1 param[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_validator.py; same validator, same result.
Show parametersHide parameters
textstringrequiredThe full text of BOOK.md
Checked by Serverdex with a plain initialize + tools/list call to mcp.ilang.ai/mcp, no credentials, about once a day. A failed check is never a removal.
On GitHub
read Nov 14, 2026- Stars
- 10
- Forks
- 1
- Last push
- Nov 12, 2026
- License
- MIT
HTML
From the README
What iLang is. iLang is I Language, the native language of AI; in human terms, a protocol. The full statement is on ilang.ai. iLang — The native language of artificial intelligence. Website · Specification · Research · AI See · Dictionary · 🤗 Hugging Face iLang is I Language. The protocol agents understand each other by. iLang is a protocol for AI, not a language for people to memorise. You keep saying what you want in your own words; your AI loads iLang and works by it. • You chat with an AI: copy the latest iLang runtime, or press Copy latest iLang on ilang.ai, and paste it into ChatGPT, Claude, Gemini, DeepSeek, Qwen or any other assistant. • You build with an API: pip install ilang-protocol or npm install ilang-protocol, then messages = ilang.wrap(messages). The loader fetches the official runtime, checks it and adds it to every request. • You use an MCP client: connect https://mcp.ilang.ai/mcp once (Claude Code: claude mcp add --transport http ilang https://mcp.ilang.ai/mcp), and your AI loads iLang itself. Everything below is for AI, developers, researchers and anyone auditing the protocol. • Official site: https://ilang.ai • Specification: https://ilang.ai/spec/ • Concept DOI: 10.5281/zenodo.21821452 • Creator: Long Quan Zhu (Max, @SUN), ORCID https://orcid.org/0009-0004-4540-8082 • Company: iLang Inc. Abstract Like HTTP standardized web communication and SQL standardized database queries, iLang standardizes how humans talk to AI.…
Read the full README on GitHub →Remotes
- streamable-http
https://mcp.ilang.ai/mcp
iLang: questions people ask
- Is iLang a remote or a local MCP server?
- According to its entry in the official MCP registry, iLang ships as a hosted endpoint (streamable-http) that your client connects to by URL.
- Does iLang need an API key?
- Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 19, 2026. Individual tools may still ask for a key when called.
- Is iLang still maintained?
- Active: the repository's last commit 6 days ago. Last push Nov 12, 2026, 10 GitHub stars, MIT licence. Read from GitHub on Nov 14, 2026.
- What tools does iLang expose?
- 9 tools as listed by the server itself during the live check, including ilang_runtime, ilang_runtime_lite, ilang_full, ilang_validate, ilang_lookup. The full list with parameters is in the Live check section above.
- How do I add iLang to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More Other servers
Browse all Other →Inflow
inflowpayai
MCP Server for agents to onboard, pay, and provision services autonomously with InFlow
INITE Atlas
inite-ai
AI tools catalogue for agents: match a need to tools, compare prices, see price and API changes.
INITE Visibility, signed in
inite-ai
AI visibility for your account: the full audit, a weekly watch, your audits, a licence.
DSAIL
JaxonAI
Turn a written policy into rules a program can check, and get the same answer every time.
Just Domain.
just-done
Check a domain name, both prices and whether it can transfer in. You register it on justdomain.ai.
KeepState
Keepstateai
Durable agent sessions: start, watch, message and pause KeepState agents; approvals ask a person.
Add the badge to your site
Show visitors that iLang is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/ai-ilang-mcp?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="iLang — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/ai-ilang-mcp?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.