
Codeitall
- Updated May 27, 2026
- codeitalldev/codeitall
codeitall is a MCP server that acts as a behavioral oracle for Rust crate APIs, advisories, yanks, deprecations, and signature search.
About
codeitall is a hosted Model Context Protocol server aimed at Rust developers who want agents to reason about crates with more than docs.rs summaries. It advertises runtime behavior insight, yank and advisory awareness, deprecation tracking, and signature search so you can validate whether a crate API fits your project before you lock versions in Cargo.toml. Developers using Claude Code or Cursor on Rust CLIs, agents, or API services can register the HTTP remote during backend work instead of manually cross-checking advisories and deprecated paths. It complements local rust-analyzer by supplying packaged ecosystem facts the agent can cite in plans and diffs. Treat it as a specialized oracle: best when your workflow is Rust-heavy and you want fewer surprise breaking changes or pulled crates after you ship.
- Behavioral oracle for Rust crate APIs including runtime behavior context
- Yank and security advisory awareness for crates.io dependencies
- Deprecation signals and signature search for targeted API lookup
- Hosted MCP at api.codeitall.dev/mcp (streamable HTTP), version 0.1.0
Codeitall by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport http codeitall https://api.codeitall.dev/mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Transport | HTTP |
|---|---|
| Auth | None |
| Last updated | May 27, 2026 |
| Repository | codeitalldev/codeitall ↗ |
What it does
Let your agent verify Rust crate API behavior, advisories, yanks, deprecations, and signatures before you commit dependency changes.
Who is it for?
Best when you want MCP-backed crate intelligence during implementation and dependency upgrades.
Skip if: Pure frontend or non-Rust stacks, or teams that need full offline crate indexing without a hosted service.
What you get
Your agent can query codeitall for crate behavior and risk signals while you edit Rust backend code and dependencies.
- Agent-grounded answers on crate runtime behavior and API signatures
- Earlier visibility into yanks, advisories, and deprecations during edits
By the numbers
- Server version 0.1.0
- Single streamable-HTTP remote at api.codeitall.dev/mcp
- Capabilities listed: runtime behavior, yank/advisory, deprecation, sig search
README.md
codeitall — Rust API behavioral oracle
Version-pinned behavioral oracle for Rust package APIs, built for AI coding
agents. Five deterministic tools backed by a Postgres substrate of
66,549,370 pattern_records and 107 successful probe runs across
7 task families (datetime, duration, base64, JSON strict-vs-permissive,
JWT verify, AEAD encrypt/decrypt, constant-time compare).
Hosted, free, no signup: https://api.codeitall.dev
This repository is codeitall's public surface — the API reference, OpenAPI spec, the "For AI Agents" page, and the per-family pages. The ingest/indexer and server source are not redistributed; you consume codeitall by querying the hosted API, not by running it yourself.
What it answers
The differentiator from a docs RAG: the substrate captures runtime behavior (what a function actually does on a canonical input set, observed empirically), not just documentation (what it claims to do). It targets the documentation-vs-runtime gap — yank status, RustSec advisories, deprecation renames, and cross-implementation behavior tables.
Tools
| Tool | Use it for |
|---|---|
answer_api_question |
Open-ended Rust API questions; routes deterministically (rule-based, no LLM) and falls back to bge-m3 cosine retrieval. |
signature_search |
You know the signature shape (fn(&str) -> Result<Vec<u8>, _>); get ranked candidate functions + crate, downloads, yank status. |
behavior_lookup |
A specific (crate, fn_name); get the probe-observation table verbatim — each row (input, outcome=ok|err|panic, value_or_error). |
compare_implementations |
A task category (e.g. "base64 crates"); get the side-by-side cross-implementation behavior table. |
find_modern_equivalent |
A suspected-deprecated call; get the current canonical alternative + yank/advisory rows. |
Determinism contract
No generative LLM sits between a request and its response. Every response is SQL + deterministic templating; the only model in the hot path is bge-m3, a deterministic text→vector embedder used for the cosine fallback (same input → same vector → same hits). This is a regression-pinned invariant.
Quickstart
# Mint a free anonymous key (no email, no signup):
curl -sX POST https://api.codeitall.dev/v1/keys \
-H 'content-type: application/json' -d '{}'
# Ask a question (HTTP REST):
curl -sX POST https://api.codeitall.dev/v1/answer_api_question \
-H 'content-type: application/json' \
-d '{"question":"how do I parse a duration string in rust"}'
GET aliases exist for every tool (browse-only clients); signature_search
also accepts a shape_b64 (base64url) parameter so URL re-encoding can't
mangle type-signature characters.
Access modes
- MCP — SSE/HTTP at
https://api.codeitall.dev/mcp(Bearer key), or stdio for self-hosters. - HTTP REST —
POST/GET /v1/<tool>. - OpenAPI 3.1 —
openapi.json(live:https://api.codeitall.dev/openapi.json).
Docs in this repo
for-ai-agents.html— positioning, tool list, key snippet (live:https://api.codeitall.dev/for-ai-agents.html).api-reference.html/api-reference.md— generated tool reference + scope/coverage.agents/— one page per probe family.
Cost & limits
Free. Per-IP key issuance cap (10/day) and per-key quota (10,000/day). No paid tier, no email capture, no signup.
Recommended MCP Servers
How it compares
Rust-focused hosted MCP oracle, not a general code-pathfinder or docs-only web search skill.
FAQ
Who is dev.Codeitall/Codeitall for?
Rust-focused developers and agent users who want structured crate API, advisory, and deprecation context inside MCP workflows.
When should I use dev.Codeitall/Codeitall?
Use it during Build backend work when you add or upgrade crates, refactor against signatures, or need yank/advisory checks before merge.
How do I add dev.Codeitall/Codeitall to my agent?
Register the streamable-HTTP remote https://api.Codeitall.dev/mcp in your MCP client; see https://api.Codeitall.dev/for-ai-agents.html for agent-specific notes.