tunnelmind.ai is hosted on Cloudflare. It measures traffic with Cloudflare Web Analytics.
| Technology | Version | First seen |
|---|---|---|
| Frontend Build Tools & CSS2 | ||
| – | 7 Nov 2026 | |
| – | 7 Nov 2026 | |
| CDN & Hosting1 | ||
| – | 7 Nov 2026 | |
| Analytics & Tag Management1 | ||
| – | 7 Nov 2026 | |
| Fonts & Icon Fonts2 | ||
| – | 7 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
route1.mx.cloudflare.netroute2.mx.cloudflare.netroute3.mx.cloudflare.netelliot.ns.cloudflare.comveda.ns.cloudflare.comgoogle-site-verification=IDzTh8QSZypHjufsdi1yyKrIeb9B2HMVjo4VtVD2nbkv=spf1 include:_spf.mx.cloudflare.net ~allprotonmail-verification=5e06b54afdb2abb96b2746de99253be74ed108d1v=MCPv1; k=ed25519; p=Af8AJJTyUEegVoJNcvOCYJAn2uO/ORHPWw9mp3+iF+I=# TunnelMind robots.txt # # TunnelMind is built specifically for autonomous agents — they are not # adversaries here, they are the primary user. Everything below /api/, # https://data.tunnelmind.ai/openapi.yaml, /oai/, /atap/, /standards, /llms.txt, # /agent-manifest.json, and /.well-known/ai-services.json is meant to be # discovered and called by AI clients. # # Be a good citizen anyway: identify yourself with a real User-Agent, # honour 429 backoff, and prefer the MCP endpoints below over scraping # rendered HTML. # # MCP servers (Streamable HTTP, both listed in the official MCP registry): # https://mcp-data.tunnelmind.ai/mcp (ai.tunnelmind/data — 108 tools) # https://mcp.tunnelmind.ai/mcp (ai.tunnelmind/scry — 12 tools) # # Discovery card: # https://tunnelmind.ai/.well-known/ai-services.json # https://tunnelmind.ai/agent-manifest.json # https://tunnelmind.ai/llms.txt User-agent: * Allow: / Sitemap: https://tunnelmind.ai/sitemap.xml
# TunnelMind
> See the internet. See the agents on it. Four instruments (Scry / Sigil / Tracker / GhostRoute) watch the network directly and record only what they witness, on one signed corpus, plus a fused cross-lens answer no siloed incumbent can compute. Where an instrument has not observed something, the record says so. Built specifically for autonomous agents.
TunnelMind answers the question an agent is actually asking when it transacts with a new endpoint: *is this real?* GreyNoise and Spur can tell you which IPs scan the internet but not which of those IPs are the egress for an SSP carrying a hundred thousand publisher relationships. DoubleVerify, IAS, HUMAN and Pixalate can tell you which supply paths look fraudulent but not which of those paths source traffic from IPs the network has logged scanning for Log4Shell. We own both halves.
Every observation in the corpus is Ed25519-signed at the sensor before it reaches the corpus, so the data can prove its own provenance. Every observed actor gets a permanent free-to-resolve handle (OAI). Every fused verdict ships with a 5-minute signed `sigil_token` plus an optional ATAP witness event chained onto the calling agent's identity token, so the agent leaves behind a verifiable trail in the same request.
## Direction (2026-11)
TunnelMind is run as an auditable autonomous company: every decision, purchase and change is meant to end as a public, signed receipt ([change ledger](https://tunnelmind.ai/changes)). The product this leads to is an accountability kit for teams whose agents spend money: what the agent saw, when, which rule fired and why, every refused action included, verifiable offline. It is not packaged for sale yet. The public demo is the [weather agent](https://tunnelmind.ai/weather), in paper mode since 2026-10-28. The Conduct Log Commons ([conduct log](https://tunnelmind.ai/conduct/)) stays free to report to and free to read.
## Standards (free, open, citation-grade)
- [OAI v1.0](https://tunnelmind.ai/oai/standard): Observed Actor Identifier — permanent, free-to-resolve handles for every actor on the network
- [Signed Attribute Bundle v1.0 (draft)](https://tunnelmind.ai/standards/attribute-bundle/v1): the output contract of a Policy Information Point — per-source coverage tri-state (observed_clean / never_observed / degraded), freshness contract (valid_until, stale_if_error), Ed25519 signature binding. Public comment closed 2026-10-24.
## Live data surfaces
- [The radar](https://tunnelmind.ai/): live sample of the corpus, no account required
- [Data API (Sigil + GhostRoute + Cross-lens)](https://data.tunnelmind.ai): `POST /v1/verify/{node}` is the fused-verdict endpoint
- [GhostRoute (routing / sovereignty)](https://data.tunnelmind.ai/v1/ghostroute/check/api.anthropic.com): origin AS, RPKI validity, claimed-vs-actual sovereign zone, first-party CT witness; `/v1/ghostroute/{check,witness,proofs}`
- [Scry API](https://api.tunnelmind.ai): `GET /v1/check/{ip}` and `/v1/check-domain/{host}`
- [Agent verification](https://data.tunnelmind.ai/v1/verify/agent/66.249.64.10?ua=Googlebot): is a claimed crawler real? UA claim vs the operator's published IP ranges (Googlebot, Bingbot, GPTBot, PerplexityBot)
- Web Bot Auth verification: `POST data.tunnelmind.ai/v1/verify/agent/signature` — neutral third-party check of an RFC 9421 agent signature against the agent's own published key directory. Relay the received Signature / Signature-Input / Signature-Agent headers + authority; get back state (verified / invalid_signature / unknown_key / directory_unreachable / expired / malformed) + per-check facts. Works independent of any CDN.
- Safety scans (public, no key): `POST /v1/scan/mcp` reads another MCP server's tools/list and scans it for injection patterns + over-broad capabilities before you wire it in; `POST /v1/scan/injection` scans any text before it reaches your model
- [Weather agent receipts](https://tunnelmind.ai/weather): a paper-money agent's every forecast, bet and refusal on Kalshi daily-high markets, each a signed receipt, published win or lose; the log in the offline verifier's layout is at `tunnelmind.ai/weather/log/v1/` (`index.json`, `files.txt`)
- [Change ledger](https://tunnelmind.ai/changes): every agent-made change to TunnelMind, newest first, each with a signed receipt (`GET data.tunnelmind.ai/v1/ledger?source=changes`)
- Agent records (free): a key's record in the Conduct Log Commons. `GET data.tunnelmind.ai/v1/tollbooth/agents` lists the keys, `/v1/tollbooth/agents/<key>` returns one key's record; MCP tool `agent_record`
- [OpenAPI 3.1 spec](https://data.tunnelmind.ai/openapi.yaml) — also the non-MCP entry: Gemini / Google ADK function-calling consume it directly
## MCP servers (agent-native entry)
Both are listed in the official MCP registry at `registry.modelcontextprotocol.io`. Look them up by name to get the canonical record.
- `ai.tunnelmind/data` — Data API surface at `https://mcp-data.tunnelmind.ai/mcp` (Streamable HTTP, 108 tools, auto-generated from OpenAPI, OAuth) — as of 2026-11-06
- `ai.tunnelmind/scry` — Scry-only surface at `https://mcp.tunnelmind.ai/mcp` (Streamable HTTP, 12 tools, no auth)
`ai.tunnelmind/sigil` was retired 2026-08-22 — every one of its tools duplicated the Data API surface. Sigil REST endpoints (`/v1/sigil/*`) and the Sigil lens are unaffected. The `cross_lens_verify` tool lives on the Data API surface (also REST `POST /v1/verify/{node}`).
## Agent onboarding
If you are an autonomous agent reading this: skip the pages written for people and read `https://tunnelmind.ai/agent-onboarding.md`. It walks the full 5-call golden path (preflight → verify → receipt → EAT → revocation check) with concrete curl examples. Written for you, not for a human.
## BYOM analyst config (bring your own model)
To configure your LLM runtime as a TunnelMind analyst — system prompt + tool subset + response schema + attestation tiers, in one fetch — use either of:
- REST: `GET https://data.tunnelmind.ai/v1/config/analyst` (content-negotiated; `?surface=data|scry|sigil`, `?receipt=true` for a Receipt v1.0 wrap)
- MCP: `prompts/get { name: "tunnelmind_analyst" }` on **either MCP**. Each MCP's default surface matches its scope so an arg-less call returns the right shape:
- `mcp-data.tunnelmind.ai` → defaults to `surface=data` (full tool set)
- `mcp.tunnelmind.ai` → defaults to `surface=scry`
Bundle is inline-signed (Ed25519, verifiable against `/.well-known/receipt-signing-key.json`). TunnelMind doesn't run your inference — you bring the model, we ship the config and meter the data API calls your analyst makes.
## Proposed (measuring demand)
- `POST https://data.tunnelmind.ai/v1/hop-receipts` — per-hop fact receipts for multi-agent graphs. Proposed, not built: returns 404 today. Each call is counted as demand.
## Discovery
- [.well-known/ai-services.json](https://tunnelmind.ai/.well-known/ai-services.json): full machine-readable service card
- [agent-manifest.json](https://tunnelmind.ai/agent-manifest.json): products, endpoints, MCP servers, pricing
- [agent-onboarding.md](https://tunnelmind.ai/agent-onboarding.md): 5-call golden path for agents
- [.well-known/atap.json](https://tunnelmind.ai/.well-known/atap.json): ATAP discovery
- [.well-known/receipt-signing-key.json](https://tunnelmind.ai/.well-known/receipt-signing-key.json): receipt verifier keys
- [.well-known/data-api-signing-key.json](https://tunnelmind.ai/.well-known/data-api-signing-key.json): data API response attestations and sigil_token key (not for v1.0 receipts)
- [.well-known/receipt-revocations.json](https://tunnelmind.ai/.well-known/receipt-revocations.json): revocation feed
- [.well-known/x402.json](https://tunnelmind.ai/.well-known/x402.json): x402 payment surface discovery
- [robots.txt](https://tunnelmind.ai/robots.txt)
## Pricing for agents
- All identifiers resolve for free, forever. The radar sample is public. 100 req/day (10/min) without a key on the Data API.
- Depth and scale: a free API key (`POST data.tunnelmind.ai/v1/keys/free`); paid machine calls settle per request with x402 (USDC on Base). The one price schedule is signed at `data.tunnelmind.ai/v1/pricing`.
- x402 v1 demo endpoint at `data.tunnelmind.ai/v1/x402/echo` for client validation without real USDC. See `/.well-known/x402.json`.
## Operator and transparency
- [Warrant canary](https://tunnelmind.ai/canary.json): monthly
- [Reference verifier source](https://github.com/TunnelMind/receipt-verify): the public verification kernel — receipt verifier, offline log verifier, OPA guide. Apache-2.0.
- Single-operator project. No venture capital. No board. No quarterly plan.
## Contact
For agentic onboarding questions, autonomous-agent issues, or to request a new MCP tool: `agents@tunnelmind.ai`.
Contact: mailto:legal@tunnelmind.ai Expires: 2027-10-06T00:00:00.000Z Preferred-Languages: en Canonical: https://tunnelmind.ai/.well-known/security.txt
| – |
| 7 Nov 2026 |