Axint is listed as active in the registry but did not answer our last check. 434 installs a week from pypi. It exposes 36 tools. Last commit 21 Sep 2026.
Proof and repair for Apple coding agents: validate Swift, run Xcode evidence, and repair failures.
Installs per day
peak 88 · avg 21 · +84% w/w
a month agotoday
Uptime history
51 days of history · worst day 94%
51 days agonow
94.5%
Uptime 24h
86 of 91 checks
36
Tools
read from the server
242 ms
Response time
average over 24h
434
Installs / week
npm and PyPI
What the code does
We read the source, 7 h ago · tools taken from the live server · rules 3dff92dd89df
A tool parameter reaches a dangerous call
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
A tool parameter reaches a dangerous call
axint.swift.fix.file → python/axint/mcp_server.py:1203, axint.swift.validate.file → python/axint/mcp_server.py:1203
completed = subprocess.run(
Capabilities
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
Runs an external command
python/axint/mcp_server.py:1203, [пакет] axint/mcp_server.py:1206
completed = subprocess.run(
Reads files and sends them to the network
python/axint/cli.py:401, [пакет] axint/cli.py:401, src/feedback/auto.ts:6
entries = [e.name for e in target_dir.iterdir() if not e.name.startswith(".")]
In the project's build, not in the package
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
Builds a database query by concatenation
.github/workflows/wwdc-nightly.yml:58
- name: Update snapshot
if: ${{ inputs.snapshot }}
Runs an external command
src/cli/login.ts:58, src/cli/mcp-install.ts:271, src/cli/status.ts:161 и ещё 6
spawn(openCmd, [verification_uri], { stdio: "ignore", detached: true }).unref();
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
A tool parameter here reaches a dangerous call
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
run in your terminal
claude mcp add axint --transport http https://mcp.axint.ai/mcp~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"axint": {
"url": "https://mcp.axint.ai/mcp"
}
}
}~/.codex/config.toml
[mcp_servers.axint]
url = "https://mcp.axint.ai/mcp".cursor/mcp.json
{
"mcpServers": {
"axint": {
"url": "https://mcp.axint.ai/mcp"
}
}
}.vscode/mcp.json
{
"mcpServers": {
"axint": {
"url": "https://mcp.axint.ai/mcp"
}
}
}Available tools 36
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
axint
axint.activate
Run a source-free compiler smoke test through the real Axint pipeline. Use immediately after installing or connecting Axint so the current agent proves it did more than start the MCP server. Use: call immediately after install or first MCP connection; use validate or run for project checks. Inputs: format changes rendering only; the smoke test has no project inputs. Effects: read-only built-in compiler smoke test; writes no files and uses no network.
axint.agent.advice
Ask the local Axint project brain what this agent should do next. Reads project context, latest run proof, latest repair plan, and active file claims, then returns host-specific guidance for Xcode, patch-first editors, or another agent lane. Use: use when local proof should choose the next move; use suggest for greenfield ideas and repair for known bugs. Inputs: cwd selects local context; question and modifiedFiles focus the next-move recommendation. Effects: reads local Axint context/proof and may refresh advice artifacts; no network.
axint.agent.claim
Claim files before an agent edits them so other agents do not patch the same SwiftUI/App files concurrently. Claims are local, short-lived, and stored in .axint/coordination/claims.json. Use: use before editing shared files in parallel-agent work; release claims when done. Inputs: agentId and files identify the claim; ttlMinutes bounds ownership and force overrides stale claims. Effects: writes local coordination claims under .axint/coordination; no network.
axint.agent.install
Install the local Axint multi-agent project brain. Writes .axint/agent.json, .axint/context/latest.*, and .axint/coordination files so AI agents, Xcode, and humans coordinate through the same local truth layer. Use: use once per project to create local multi-agent coordination; not needed for one-off compile. Inputs: cwd scopes local coordination; projectName and hosts shape generated project-brain files. Effects: writes .axint/agent, context, and coordination files; no network.
axint.agent.release
Release active local Axint file claims for this agent after finishing or abandoning a task. This keeps parallel agents and Xcode from blocking each other on stale claims. Use: use after finishing or abandoning claimed files; use agent.claim before edits and agent.advice for next steps. Inputs: agentId releases only its matching claims unless files narrow the release set. Effects: updates local coordination claims under .axint/coordination; no network.
axint.cloud.check
Run an agent-callable Cloud Check against Swift or Axint TypeScript source. Accepts inline source or a sourcePath, then returns a Cloud-style verdict, Apple-specific findings, next steps, an AI repair prompt, and a redacted compiler feedback signal when the check finds a bug. Use: use for Apple-aware source review and repair prompts; provide evidence for UI/runtime claims. Inputs: provide source or sourcePath, not both; evidence fields strengthen UI and runtime claims. Effects: read-only response from provided source/path; may use configured Cloud Check endpoint; no source is sent unless.
axint.compile
Compile TypeScript source (defineIntent() call) into native Swift App Intent code. Returns { swift, infoPlist?, entitlements? } as a string — no files written, no network requests. On validation failure, returns diagnostics (severity, AX error code, position, fix suggestion) instead of Swift. Use: use when TypeScript DSL source should become Swift; use validate for cheaper preflight only. Inputs: source is TypeScript DSL text; options add sandbox, format, plist, or entitlement proof without writing files. Effects: read-only generated Swift/diagnostics; writes no files and uses no network.
axint.context.docs
Return the project-local Axint docs context that agents should reload after new chats or context compaction. This is the durable docs memory that keeps the agent using Axint instead of forgetting the workflow. Use: use after compaction when the agent needs workflow docs without rereading the whole site. Inputs: cwd selects project docs context; include sections only when the longer runbook is needed. Effects: read-only generated docs context; writes no files and uses no network.
axint.context.memory
Return the compact Axint operating memory that agents should reload at new chat start, after context compaction, or after long coding drift. Use this to keep Axint top-of-mind without rereading the full docs. Use: use after compaction or session restart for compact operating rules; use context.docs for longer workflow docs. Inputs: cwd selects project memory; format changes rendering without changing content. Effects: read-only generated context; writes no files and uses no network.
axint.doctor
Audit the current Axint runtime and project wiring: running MCP version, expected version, Node/npm/npx paths, project .mcp.json, AGENTS.md, CLAUDE.md, .axint/project.json, and Xcode Claude Agent registration. Use this when an agent might be connected to a stale Axint process or when a new project needs first-try MCP setup proof. Use: call when MCP wiring, package paths, Xcode setup, or project memory may be stale; use run for build proof. Inputs: cwd selects the project; expectedVersion turns a runtime mismatch into a blocker. Effects: read-only inspection; writes no files; no auth or network required.
axint.feature
Generate a scaffolded Apple-native feature package from a description. Returns multiple files: compile-aware Swift source, companion widget/view, Info.plist fragments, entitlements, and XCTest scaffolds — all structured file-by-file so an Xcode agent can write each file directly into the project. Use: use for new Apple-native surfaces; not for repairing existing app bugs. Inputs: description is the feature brief; kind and platform constrain the generated package. Effects: read-only generated output; writes no files and uses no network.
axint.feedback.create
Create or read a privacy-safe learning packet for Axint repair intelligence. Packets include project shape, diagnostic codes, issue class, redacted evidence, and likely product owner, but never include source code. Users can inspect the JSON before sending it to Axint Cloud. Use: create a privacy-safe issue packet when output was weak, or read the latest packet; never use it to send source. Inputs: latest reads instead of creates; outcome and diagnostic fields stay source-free unless excerpts are explicit. Effects: writes or reads redacted .axint/feedback packets; never includes source by default.
axint.fix-packet
Read the latest Fix Packet that Axint emitted locally after a compile or watch run. Returns the exact repair artifact that AI tools or Xcode helpers should consume next: verdict, top findings, full diagnostics, next steps, and an AI-ready fix prompt. Use: use after a local compile/watch/check emitted a packet; not a new analysis pass. Inputs: cwd and path locate an existing packet; latest selects the newest artifact and never reruns analysis. Effects: read-only local artifact read; writes no files and uses no network.
axint.project.index
Scan the local Apple project and write a compact .axint/context pack so Axint can reason over changed files, nearby SwiftUI surfaces, and interaction-risk files instead of only one source file at a time. Use: use before project-aware repair, multi-file SwiftUI work, or interaction-risk analysis. Inputs: changedFiles seed related-file discovery; dryRun returns the pack without writing .axint/context. Effects: writes .axint/context unless dryRun=true; reads local project files only.
axint.project.pack
Generate the Axint project-start pack for a new Apple app without writing files. Use: use to bootstrap a new Apple project with Axint instructions; use project.index to inspect an existing project. Inputs: cwd and projectName identify the project; host choices control generated integration files. Effects: read-only generated file pack; writes no files and uses no network.
axint.project.syncVersion
Update Axint-owned project-pack version hints after an upgrade. Use this after axint.upgrade or npm/pip upgrades so .axint/project.json, AGENTS.md, CLAUDE.md, and Axint rehydration docs stop pointing agents at an older package version. Use: use after package upgrades so local project-pack hints stop naming old Axint versions. Inputs: cwd scopes Axint-owned files; targetVersion overrides running version; dryRun prevents writes. Effects: updates Axint-owned project instruction files unless dryRun=true; no network.
axint.registry.search
Search the Axint Registry for already-published packages that match a natural-language query. Use this BEFORE calling axint.feature or axint.compile so the agent can install an existing package instead of regenerating Swift the community has already shipped. Use: use before generating code to find reusable packages; not for validating local Swift. Inputs: query drives ranking; kind and platform narrow results without changing the registry source. Effects: read-only local registry search using AXINT_REGISTRY_PATH or sibling checkout; no network by default.
axint.repair
Plan a project-aware Apple repair for existing apps. Indexes the local project, classifies build/UI/runtime evidence, runs Cloud Check when source is provided, ranks likely SwiftUI/App files, returns a host-aware patch/proof plan, and writes .axint/repair plus a privacy-safe .axint/feedback packet. Use: use for existing app bugs with logs, UI symptoms, or runtime evidence; not for greenfield generation. Inputs: describe the observed bug and attach logs or evidence; modifiedFiles and project index narrow the plan. Effects: writes .axint/repair and privacy-safe .axint/feedback artifacts; reads local project files.
axint.run
Run the enforced Axint Apple build loop outside the Xcode UI. Use: use for the complete proof loop; use swift.validate, cloud.check, or fix-packet when only one stage is needed. Inputs: integration=minimal enforces local advisory no-fix behavior; background returns a job id; outputDir controls artifacts. Effects: starts child processes, writes .axint/run artifacts, may run xcodebuild/tests, and may call Cloud Check.
axint.run.cancel
Cancel the latest or selected Axint run by killing active child process groups. Use this when xcodebuild or a UI-test runner survived an MCP timeout or transport close. Use: use only to stop an active run or stuck child process group; use run.status for read-only inspection. Inputs: jobId is required; signal and grace period control escalation before killing the process group. Effects: destructive: kills active Axint child process groups; no network.
axint.run.status
Read the latest or selected Axint run job record, including active child process IDs. Use this when a long xcodebuild run may still be active after an MCP timeout or client disconnect. Use: use after MCP timeouts or long builds to inspect or rejoin; it does not start, rerun, or cancel work. Inputs: jobId selects a background run; includeLogs changes returned detail without changing the job. Effects: read-only local run/job inspection; writes no files and uses no network.
axint.scaffold
Generate a starter TypeScript intent file from a name and description. Returns a complete defineIntent() source string ready to save as a .ts file — no files are written, no network requests made. On invalid domain values, returns an error string. The output compiles directly with axint.compile. Use: use to create a small TypeScript intent starter; use templates.get for richer examples and compile for Swift output. Inputs: name must be PascalCase; params define the starter contract; domain defaults to general. Effects: read-only generated TypeScript; writes no files and uses no network.
axint.schema.compile
Compile a minimal JSON schema directly to Swift, bypassing the TypeScript DSL entirely. Supports intents, views, components, widgets, and full apps via the 'type' parameter. Uses ~20 input tokens vs hundreds for TypeScript — ideal for LLM agents optimizing token budgets. Use: use for token-light JSON-to-Swift generation; use compile for full TypeScript DSL control and scaffold for TS starters. Inputs: schema kind selects intent, view, widget, or app output; options add companion metadata. Effects: read-only Swift generation; writes no files and uses no network.
axint.session.start
Start an enforced Axint agent session. Writes .axint/session/current.json plus token-scoped session history, refreshes .axint/AXINT_REHYDRATE.md, returns compact operating memory, docs context, a session token, and the exact axint.workflow.check args. Use: call at the start of a tool-enabled agent session or after context compaction. Inputs: cwd scopes session files; prior token and context inputs preserve continuity after compaction. Effects: writes .axint/session and rehydration artifacts; no auth or network required.
axint.status
Report the exact running Axint MCP server version, package path, uptime, registered tool count, and same-thread MCP reload/update instructions. Use this as the first tool in a new AI-agent or Xcode chat to prove which Axint process the agent is actually connected to. This answers the running MCP server, not a guessed npm, PyPI, or docs version. Use: call first or after an MCP reload to prove the connected server version; do not use as an npm/PyPI lookup. Inputs: format changes rendering only; no project path is required. Effects: read-only; writes no files; no auth or network required.
axint.suggest
Suggest Apple-native features for an app based on its description. The domain is only a weak hint; the app description wins. Returns a ranked list of features with recommended surfaces (intent, widget, view, component, store, app), estimated complexity, and a one-line description for each. Use: use before generation to choose Apple surfaces; not a substitute for registry search or validation. Inputs: prompt is the product brief; dir adds project context; Pro mode is used only when configured. Effects: local mode is read-only; Pro mode may call Axint endpoint when credentials are configured.
axint.swift.fix
Auto-fix mechanical Swift errors detected by axint.swift.validate. Use: use after swift.validate when errors are mechanical; inspect remaining diagnostics manually. Inputs: source is required; codes limits mechanical rewrites; maxPasses bounds convergence attempts. Effects: read-only fixed-source output; writes no files and uses no network.
axint.swift.validate
Validate existing Swift source against Axint's Apple-specific build-time rules (AX700–AX749) including Swift 6 concurrency and Live Activities. Use: use on generated or edited Swift before build; pair with swift.fix for mechanical repairs. Inputs: source or sources provide Swift text; projectIndex enables cross-file checks; platform filters rules. Effects: read-only Swift diagnostics; writes no files and uses no network.
axint.templates.get
Retrieve the full TypeScript source code of a specific bundled template by id. Returns a complete, compilable defineIntent() file as a string — ready to save as .ts and compile with axint.compile. Includes perform() logic, parameter definitions, and domain-specific patterns. Use: use after templates.list to fetch a complete reference template; edit it before calling compile. Inputs: id must come from templates.list; format changes source versus metadata rendering. Effects: read-only template source; writes no files and uses no network.
axint.templates.list
List all bundled reference templates in the Axint SDK. Returns a JSON array of { id, name, description } objects — one per template. Templates cover messaging, productivity, health, finance, commerce, media, navigation, smart-home, and entity/query patterns. No input parameters required, no files written, no network requests, no side effects. Use: use to discover valid template ids before templates.get. Inputs: category and query filter metadata; call without filters to discover every valid id. Effects: read-only template metadata; writes no files and uses no network.
axint.tokens.ingest
Ingest design tokens from JSON, JS/TS object exports, or CSS variables and return a SwiftUI token enum. Use this before generating Swarm-style views/components so agents can preserve exact brand colors, dimensions, radii, spacing, and typography. No files are written. Use: use before view/component generation when a design system should be preserved. Inputs: tokens accepts structured design values; enumName and accessLevel shape generated Swift names. Effects: read-only Swift token output; writes no files and uses no network.
axint.upgrade
Check the latest Axint package and optionally apply the upgrade while preserving the current agent thread. Use: call when axint.status shows a stale server; not for app dependency upgrades. Inputs: apply defaults false; targetVersion selects the install, while reinstallXcode and writeReport matter only when applying. Effects: destructive when apply=true: can run package installs, refresh Xcode wiring, and write .axint/upgrade; may use npm.
axint.validate
Validate a TypeScript intent definition without generating Swift. Runs the full Axint validation pipeline (134 diagnostic rules) and returns a JSON array of diagnostics: { severity: 'error'|'warning', code: 'AXnnn', line: number, column: number, message: string, suggestion?: string }. Returns an empty array [] when validation passes. Use: use for TypeScript DSL diagnostics before Swift output; use swift.validate for existing Swift. Inputs: source is TypeScript DSL text; strictness options affect diagnostics only and never emit Swift. Effects: read-only diagnostics; writes no files and uses no network.
axint.workflow.check
Agent workflow gate that records a local freshness stamp. Requires the current Axint session token from axint.session.start unless requireSession=false is explicitly set. Use: use at stage gates to prove workflow coverage; use status for version checks and run for build/test proof. Inputs: stage selects the gate; sessionToken proves continuity; allowNoSession is an explicit escape hatch. Effects: writes a local .axint/session workflow freshness stamp; edits no app source and uses no network.
axint.xcode.guard
Guard an Xcode agent session against context compaction and Axint drift. Checks project memory files, active Axint session, latest Axint Run or guard proof, and long-task freshness. Use: call around long Xcode tasks, context recovery, broad Swift edits, or before claiming runtime proof; use workflow.check. Inputs: stage selects the gate; modifiedFiles and notes narrow drift checks; autoStartSession defaults true. Effects: writes .axint/guard proof and may start a session; does not edit app source or use network.
axint.xcode.write
Write a file inside the Xcode project through the Axint guard path. For Swift files, runs axint.swift.validate and axint.cloud.check immediately, then records .axint/guard/latest.* proof. Use this instead of raw XcodeWrite when an agent is editing Apple-native files during a long task. Use: use only for guarded Xcode-project file writes; outside Xcode, patch normally and validate after. Inputs: path must remain inside cwd; createDirs, validateSwift, and cloudCheck default true. Effects: writes the requested file inside cwd, may create dirs, validates Swift, and may write guard/check artifacts.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.axint.ai/mcp | streamable-http | answering | 8046 ms | 1 min ago |
Alternatives to Axint
same job, measured the same wayFailTrace
by lbarimi
Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.
Volato Errors
by volato
Read-only production error evidence for coding agents investigating failures.
Code Factory
by zrk222
Local proof facts for AI coding clients: intent, tests, Graph Ops, and review evidence.
Sinter
by shellfu
Persistent, evidence-backed code graph for coding agents.
Fable Mode
by rex-codebase
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
ProofFlow
by hyperion-gpu
Audit infrastructure for AI coding agents with evidence-backed review and policy gates.
Elite Reasoning MCP
by snehgabani
Evidence-gated verification, selection, and measurement MCP for coding agents.
Misakanet
by ikalus1988
Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
Axint — questions
Answers built from our own checks of this server.
What can Axint do?
It exposes 36 tools, read directly from the server on our last check. Among them: axint.activate, axint.agent.advice, axint.agent.claim, axint.agent.install, axint.agent.release, axint.cloud.check and 30 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Axint working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 86 of 91 checks got a reply (94.5%), average response time 242 ms. The bar chart above shows every period we have measured.
The registry lists Axint as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Axint?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Axint need an API key?
No. Axint completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 36 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Axint?
It answers our handshake in 242 ms on average, which is faster than 62% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Axint?
The npm package @axint/compiler was installed 434 times in the last week. Week over week that is +84%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Axint open source?
Yes — it is published under the Apache-2.0 licence, written in TypeScript, 17 stars on GitHub and 22 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.