AXIS Iliad MCP Server

Axis' Iliad

Axis' Iliad — The modern epic that shapes raw codebases into canonical, agent-ready artifacts. Axis' Iliad authors the definitive foundation for the next era of natural-language workspace development.

Canonical name: Axis' Iliad. Use this name consistently across docs, registries, and integrations.

---

AXIS Ecosystem

Iliad is the x402 showcase in the Trust Fabric stack. Full registry: packages/generator-core/src/estate-registry.ts, served live at GET /.well-known/axis-estate.json (superseding ecosystem.registry.yaml, retired 2026-08-22 — see docs/ESTATE_FEDERATION_STRATEGY.md).

x402 contract: docs/x402/CONTRACT.md

---

Try it in 30 seconds — no signup required

Three programs are completely free with no API key:

# 1. Get an API key (free tier, instant)
curl -X POST https://axis-api-6c7z.onrender.com/v1/accounts \
  -H 'Content-Type: application/json' \
  -d '{"email":"you@example.com","name":"My Agent","tier":"free"}'

# 2. Analyze any public GitHub repo
curl -X POST https://axis-api-6c7z.onrender.com/v1/github/analyze \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{"url":"https://github.com/owner/repo","programs":["search","skills","debug"]}'

# 3. Download the generated artifacts as a ZIP
curl https://axis-api-6c7z.onrender.com/v1/projects/PROJECT_ID/export \
  -H 'Authorization: Bearer YOUR_API_KEY' -o artifacts.zip

Free tier includes: Search (context maps), Skills (AGENTS.md, CLAUDE.md, .cursorrules), Debug (playbooks, incident templates). Pro unlocks all 21 programs.

---

What you get

One scan → 152 artifacts across 21 programs, ready in seconds:

Plus the begin loop — hand it to an agent and say begin

Every analysis also weaves in a self-driving control loop so an AI coding agent can finish the work, not just understand it:

• begin.yaml — the loop head: the inferred goal, a human-in-the-loop protocol (the owner only answers plain-English product questions), the move-selection algorithm, and convergent stop conditions.
• continuation.yaml — the loop state: an ordered step-list of every artifact + a priority candidate queue seeded from the analysis (the goal, detected gaps, a verify-harness when no tests exist).
• A ⟳ Continue footer on every Markdown artifact; the final step self-prompts begin, closing the loop back to begin.yaml.

Download the pack (CLI, MCP, or the full-pack export), hand it to an agent, say begin — it works the queue, verifies each step, and stops when the queue is empty (convergent, never a runaway). No coding required on the owner's end.

AXIS dogfoods this on itself: this repo's own root begin.yaml / continuation.yaml are the live loop we work from, also served verbatim over REST at GET /begin.yaml / GET /continuation.yaml — so an agent crawling this API discovers the same convention without cloning the repo.

---

For AI agents — MCP integration

AXIS exposes a Streamable HTTP MCP server at https://axis-api-6c7z.onrender.com/mcp. Add it to your agent and it can analyze any repo or prepare for agentic purchasing autonomously.

VS Code (.vscode/mcp.json):

{
  "servers": {
    "axis-iliad": {
      "type": "http",
      "url": "https://axis-api-6c7z.onrender.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "axis-iliad": {
      "url": "https://axis-api-6c7z.onrender.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}

Free MCP tools (no auth needed): list_programs, search_and_discover_tools, get_install_manifest, discover_agentic_purchasing_needs, prepare_agentic_purchasing_preview, discover_estate_tools (sibling AXIS properties — payments, 3D generation, and more), plus the deterministic commerce decision engines: sca_exemption_decision, grade_compliance, assemble_ce3_evidence, build_ap2_mandate, score_dispute_readiness (evidence-capture readiness — not a dispute-win prediction). Five more are estate-flagged planned-capability stubs (Foundry Wave-1, honest redirects to Foundry's own MCP endpoint until an Iliad-hosted proxy ships): axis_validate, axis_inspect, axis_compare, axis_manifest_verify, roblox_compliance_check. get_referral_code, get_referral_credits, and iliad_network_tokenization are also free (no charge) but, unlike the tools above, do require auth. ping_payment is not free — it costs $0.005 and exercises the real x402 payment loop, the cheapest paid call in the catalog.

---

Pricing

Budget negotiation: send X-Agent-Budget: {"budget_per_run_cents": 25} + X-Agent-Mode: lite on any paid call.

---

Self-host

System Requirements

• Node.js: ≥ 20.x (LTS recommended)
• pnpm: ≥ 9.x
• OS: macOS 11+, Linux (any distro), or Windows 10+
• RAM: 4 GB minimum (8 GB recommended)
• Disk space: ~2 GB for dependencies + build

Quick Start

# Prerequisites: Node.js ≥ 20, pnpm ≥ 9
git clone https://github.com/lastmanupinc-hub/axis-iliad.git
cd axis-iliad
pnpm install
pnpm build

# Start the API server (port 4000)
node apps/api/dist/server.js

# Start the web UI (port 5173)
cd apps/web && npx vite

# Or use the CLI directly
node apps/cli/dist/cli.js analyze .
node apps/cli/dist/cli.js github https://github.com/owner/repo

Docker

docker build -t axis-iliad .
docker run -p 4000:4000 axis-iliad

Requires: Docker 20.10+ or Docker Desktop

---

Architecture

axis-iliad/
├── apps/
│   ├── api/          → Zero-dependency HTTP server (port 4000, 178 endpoints)
│   ├── cli/          → CLI tool: axis analyze <dir> | axis github <url>
│   └── web/          → Vite + React 19 SPA (dark theme, toast, command palette)
├── packages/
│   ├── snapshots/    → Snapshot intake, Postgres (Neon) persistence, billing, funnel
│   ├── repo-parser/  → Language detection (60+), framework detection (10), import graph
│   ├── context-engine/ → Context map builder, repo profile, route/architecture analysis
│   └── generator-core/ → 152 generators across 21 programs
└── vitest.config.ts  → Shared test config

Programs (21)

API Endpoints

Core Pipeline

Billing & Account

Funnel & Plans

Search & Versions

Webhooks

Infrastructure

Input Methods

1. File Upload — POST /v1/snapshots with multipart body
2. GitHub URL — POST /v1/github/analyze with { "url": "https://github.com/..." }
3. CLI (local) — axis analyze <directory> scans local files
4. CLI (remote) — axis github <url> fetches from GitHub

Tech Stack

• Runtime: Node.js 20+, TypeScript 5.7 strict
• Backend: Zero-dependency custom HTTP router, Neon Postgres (pg, async pooled)
• Frontend: Vite 6 + React 19, CSS design system (dark theme)
• Testing: Vitest 4 — ~4,900 tests across ~190 files, run against Postgres 16
• Benchmarks: Vitest bench harness (packages/repo-parser/src/perf.bench.ts, npx vitest bench) covers parseRepo at 200-file scale; no specific latency number is pinned here — this repo's own honesty policy (see packages/generator-core/src/perf-compliance.test.ts) bans citing a perf figure unless it's sourced from a checked-in, machine-generated results file, which doesn't yet exist for this bench. The 7 agentic-purchasing engines DO have one: packages/generator-core/perf-results.json (regenerate via pnpm bench:compliance).
• Build: pnpm workspaces, tsc per package
• CI: GitHub Actions (Node 20/22 matrix, coverage, dep audit, Docker build)

Development

pnpm install          # Install all dependencies
pnpm build            # Build all packages + apps
pnpm test             # Run all tests
npx vitest run        # Run tests directly
npx vitest bench      # Run performance benchmarks
npx vitest --coverage # Run tests with coverage report

See CONTRIBUTING.md for how to add a generator, endpoint, or program.

Input methods

---

Website: https://iliad.trustfabric.ai · Live API: https://axis-api-6c7z.onrender.com · Docs: https://axis-api-6c7z.onrender.com/v1/docs · MCP: https://axis-api-6c7z.onrender.com/mcp

License

Private. All rights reserved.