aifeed-protocol
This server lets you verify and consume AIFeed-signed web content: check a domain's manifest and DNS anchor, fetch token-budgeted markdown/MAKO pages, list and verify declared assets, search a signed delta index, and decide whether a specific usage is permitted on an origin.
verify_manifest — verify a domain's AIFeed manifest (signature + DNS
_aifeedanchor) and get VERIFIED/UNVERIFIED status.fetch_aifeed — fetch a page as AIFeed Markdown or MAKO, optionally truncated to a token budget, with optional signature verification via an
ed25519:…key.list_assets — list images, videos, audio, documents, and downloads declared by a signed page.
verify_asset — download a declared asset and verify its bytes against the page-declared size and SHA-256.
select_index — fetch a signed delta index and rank entries by query within page/token budgets.
decide_usage — check whether a usage (e.g. training, retrieval, quote, summarize) is allowed on a given origin.
1-Minute Quickstart
Publisher side — sign what agents may do with your content:
npx aifeed keygen --out .aifeed # Ed25519 key pair
npx aifeed site build ./public --domain example.com \
--key .aifeed/aifeed-private.pem --llms --inject # manifest + page markdown + index
npx aifeed validate ./public --domain example.com # verify locallyPrefer zero config? npx aifeed init --domain example.com --dir ./site creates the keys,
a signed manifest, and the DNS/host setup guide in one step.
Agent side — verify any domain in 3 lines:
npm install @aifeed/verifyconst { verifyRemote } = require('@aifeed/verify');
const out = await verifyRemote('example.com'); // discovery → signature → DNS anchor
console.log(out.result, out.anchor.status); // VERIFIED anchoredTypeScript: import { verifyRemote } from '@aifeed/verify';
Where to go next: Why AIFeed? · agent quickstart ·
publisher AI guide · Studio publisher app ·
npm: aifeed CLI ·
@aifeed/verify
Related MCP server: AgentVeil Protocol
Why AIFeed?
AI agents now drive a large and growing share of web traffic, but the signals that say what they may do are unsigned text files. Anyone can edit them, nothing binds them to a domain, and there is no way to revoke them. The asymmetry is measurable:
1.9 billion crawls ignored
robots.txtrules in a single half-year (one vendor).A 70,900 : 1 crawl-to-referral ratio was measured for a major AI provider.
AI bots averaged 4.2 % of HTML requests in 2025, peaking at 6.4 %.
AIFeed replaces "please respect this file" with a cryptographically verifiable declaration, plus lean agent-ready content that cuts cost on both sides.
How it works
Generate an Ed25519 key pair — the private key never leaves the origin.
Publish a signed manifest at
/.well-known/ai.json: per-use permissions (training, retrieval, quote, …), crawl limits, license, revision.Anchor the key in DNS (
_aifeedTXT) so a manifest cannot be spoofed by another domain.Agents verify the chain — TLS → domain → signature (JCS + Ed25519) → DNS anchor — and re-check a multi-signature revocation registry on every use.
Rotate keys safely — announce the successor with an old-key-signed directive (plus an advisory DNS
pk2cross-check), keep a bounded overlap, cut over, then revoke the old key permanently. Runbook:docs/rotation.md.Serve lean content under one of two profiles (below), with a signed delta index so unchanged pages cost 0 bytes.
For AI agents: the check-first guide (discovery → verification → permission
decisions → delta → failure handling) is in
docs/agent-quickstart.md,
with a runnable example at
examples/agent/compliant-agent.js.
Verify from other stacks
Independent Python package (standard library only):
pip install aifeedfrom aifeed import verify
report = verify.verify_directory('./my-site', domain='example.com')
print(report['result'], report['errors'])Prefer the repository? The same CLI is here (zero dependencies, Node ≥ 20):
cd aifeed-protocol
node bin/cli.js keygen --out keys/
node bin/cli.js validate https://example.com
node bin/cli.js site build ./public --domain example.com --key keys/aifeed-private.pemTwo content profiles
Profile | Media type | Extension | Notes |
AIFeed Markdown (native) |
|
| In-band signed policy block, token budget, translation |
MAKO (compatibility) |
|
| External MAKO trust profile, served from the same signed bytes with its own signature context |
Dual-stack origins serve both; cross-format replay is rejected by design.
Measured results
All numbers are reproducible from committed artifacts (npm run bench:mako,
npm run bench:enforcement); the test environment is a single machine on loopback
networking with a synthetic 60-page corpus. Honest baseline included.
What | Result | Label |
Conversion to markdown profiles vs HTML | −68.83 % transferred bytes | measured |
Delta consumption (10 % pages changed) | −95.73 % vs HTML crawl | measured |
Publisher egress bytes / CPU / peak connections | −55.19 % / −56.23 % / −88.24 % | measured (simulation) |
AI-side received bytes (all profiles / compliant client) | −54.84 % / −72.93 % | measured (simulation) |
Unchanged pages skipped | 14 of 18 | measured (simulation) |
Signature verification cost | 0.70 ms / page | measured |
The 30-day live pilot has not run yet; projections per 1,000 tenants are labeled as model extrapolations, and vendor claims of up to 94 % token reduction require semantic summarization this project does not perform automatically.
What's in this repository
Path | Contents |
Zero-dependency reference implementation and CLI | |
Published packages: CLI ( | |
Conformance vectors: 34 manifest · 39 MAKO · 11 AIFeed Markdown | |
WordPress plugin: signed manifest, AIFeed Markdown + MAKO dual-stack, | |
Specifications EN/ID: manifest v0.1/v0.2, AIFeed Markdown v1.0 | |
JSON Schemas for manifests, signatures, AIFeed Markdown, MAKO | |
Preprint: LaTeX source, PDF, claim ledger, arXiv bundle | |
Agent quickstart, deploy and namespace guides, Indonesian project notes | |
Zero-dependency local publisher app: crawl, declare, build, verify, export, and rotate | |
Reference implementation details, what gets verified, CLI quickstart |
Documentation
Reference implementation:
docs/REFERENCE.mdMaintenance contract (AI agents & devs):
AGENTS.mdArchitecture:
docs/architecture.md· Release guide:docs/release.mdAgent quickstart (client side):
docs/agent-quickstart.mdPublisher AI guide (owner side):
docs/publisher-ai-guide.mdPublisher Studio (local app):
studio/README.mdAgent skill:
skills/aifeed/SKILL.md(installable via ClawHub:npx clawhub install aifeed)Complete guide:
docs/penjelasan-aifeed.html(source of https://aifeed.md/penjelasan.html)Security policy:
SECURITY.mdGovernance & open-core policy:
GOVERNANCE.mdDeploying the site:
docs/deploy-site.mdarXiv submission notes:
paper/ARXIV-SUBMISSION.md
Status
Release
1.0.0-draft— the specifications are not frozen yet. Wire versions: manifest0.1/0.2, AIFeed Markdown1.0, MAKO0.2.Conformance: 34 manifest + 39 MAKO + 11 AIFeed Markdown vectors, executed by independent JavaScript and Python verifiers, plus PHP differential fixtures, 90,000+ fuzz executions, and a WordPress end-to-end test.
Not claimed: external cryptographic review and a live pilot (both pending); origin+DNS compromise is undetectable on first contact.
License and contact
Specifications CC BY 4.0 · reference code and plugin MIT · vectors CC0.
Contact: contact@aifeed.md — security reports per
SECURITY.md.
Available Tools
6 toolsdecide_usageB
Decide whether a usage (retrieval, training, summarize, …) is allowed on an origin.
Inputs: usage (required), domain (required), manifestUrl.
fetch_aifeedB
Fetch a page as token-budgeted AIFeed Markdown/MAKO with permissions and optional signature verification.
Inputs: url (required), profile, max_tokens, publicKeyValue.
list_assetsB
List the images, videos, audio, documents, and downloads a signed page declares.
Inputs: url (required), profile, publicKeyValue.
select_indexC
Fetch a signed delta index and rank entries by query within page/token budgets.
Inputs: domain (required), query, indexUrl, max_pages, +1 more.
verify_assetA
Download a declared asset and verify its bytes against the page-declared size/sha-256.
Inputs: pageUrl (required), assetUrl (required), profile, publicKeyValue.
verify_manifestA
Verify an AIFeed manifest: signature, DNS _aifeed anchor, and result (VERIFIED/UNVERIFIED).
Inputs: domain (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct primary purpose, and the set is easy to navigate. The only minor overlap is that fetch_aifeed optionally performs signature verification, which is also the focus of verify_manifest, but their main intents differ enough to avoid real confusion.
All tool names follow the same snake_case verb_noun pattern: verify_manifest, fetch_aifeed, list_assets, verify_asset, select_index, decide_usage. This makes the API predictable and easy for an agent to pattern-match.
With 6 tools, the server is well-scoped for the AIFeed protocol use case. Each tool covers a necessary operation without redundancy or bloat.
The tool surface covers the core protocol workflow: manifest verification, page fetching, asset enumeration and verification, index selection, and usage policy decisions. No obvious dead ends or critical missing operations for a consumer-focused protocol server.
Maintenance
Related MCP Connectors
Real-time data feeds for AI agents with USDC micropayments on Base for premium tools.
Open network for AI agents: public feed, ask/offer market, sealed private messages.
Trust signals for AI agents: an open agent-readiness standard and developer tool guide. Read-only.
The verifiable work layer for AI: 153 tools, cross-AI handover, a verifiable receipt for every job.
Related MCP Servers
- AlicenseAqualityCmaintenanceSimple and free publishing of content on the web for AI Agents2MIT
- AlicenseAqualityBmaintenanceTrust, identity, and reputation infrastructure for AI agents. Register agents with W3C DID (Ed25519), check EigenTrust reputation scores, submit peer attestations, search agents by capability, and verify IPFS-anchored audit trails. 11 tools.20344 PyPI16MIT
- AlicenseNot gradedqualityDmaintenanceTurns AI agents into autonomous economic actors by providing tools to discover, evaluate, acquire, and serve tokenized content on the $402 network.1MIT
- AlicenseAqualityBmaintenanceLicensing infrastructure for premium content from specialist publishers in geopolitics, finance, AI and industry. License articles for your AI product to answer from, take a publication's full catalogue, license it for training, or show it to your clients, all under one contract, with every use tracked and the publisher paid.20570 npm1MIT