formalmind bronze
docs.formal.team
“Formal Mind proves Solidity contracts correct: a swarm of agents on your own computer writes a Lean 4 proof for each function in scope, checks it with lake build, and files bugs with Foundry PoCs. Bugs, Proofs and Code show the results, read from the repository's own files. Status: early access. The desktop app is free to download for macOS (Apple Silicon and Intel) and Windows; the swarm runs locally and runs its agents on your own Claude plan (through Claude Code) or your own Anthropic or OpenAI key. The website opens public GitHub repositories with the same Bugs, Proofs and Code tabs. These tools read what is public: the audit format, Formal Mind's audit of an example repository, and the desktop app's latest release; they change nothing. The swarm runs in the desktop app. To run it, onboard a repository or read Formal Mind's files in one, read the skills at https://formal.team/.well-known/agent-skills/index.json.
https://formal.team/mcp its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Google Trust Services
domain-validated
Valid until 24 Jan 2027 as of our check on 14 Nov 2026. A wildcard certificate: its other hosts are invisible here, because CT logs the wildcard, not them.Control of the hostname was checked; nothing about who operates it.Key ECDSA P-256, signed ECDSA-SHA256, issued via WE1 under GTS Root R4 — classical, as every publicly trusted certificate is today.
Names on this certificate (3)
formal.team,docs.formal.team,*.docs.formal.team. - Connection
-
TLS 1.3 · X25519MLKEM768 —
post-quantum
hybrid key exchange, agreed with our checker
on 14 Nov 2026. The agent is served from
formal.team, so that server's operator chose this. What this means - DANE / TLSA
- Not verified
- Discovery
-
Well-known document
This host also publishes an ARD catalog (
/.well-known/ai-catalog.json) declaring 9 resources. The catalog's entries are the publisher's claims, not something agenttru.st verified. - AI use policy
-
What this site's
robots.txtsays about how AI may use its content. Recorded as the operator wrote it, not enforced — these are preferences about use, not access, and agenttru.st only reads the agent's own discovery documents. - AI-facing documents
-
Publishes
/llms.txt— “Formal Mind Docs” a curated map of the site's content for language modelsFetched from this host during verification. Neither document is how this agent was discovered. - First seen
- 14 Nov 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- MCP verified by handshake or card fetch, not merely advertised
- Hosted in
-
? Unknown
·
Cloudflare, Inc.
(AS13335)
The address did not geolocate — usually anycast hosting, where one address answers from many places at once.
- Last checked
- 12h ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of docs.formal.team controls every word below.
This card declares no skills. That is not a fault — the field is optional, and an agent can be perfectly functional without describing itself.
What kind of listing
- docs. hostname: Its hostname begins docs.
- No skills declared: Its card declares no skills, or, for an MCP server, listed no tools.
Checked by agenttru.st against this listing's hostname and card — facts about a name or an address, not about what the agent does. How kinds are decided.
What its catalog declares
From the ARD catalog this host publishes at
/.well-known/ai-catalog.json. The operator controls every entry; agenttru.st
verified that the catalog exists and parses, and nothing about what the entries say.
Formal Mind MCP servers
One card, two remotes: read-only tools at /mcp (no auth): the audit format, Formal Mind's audit of an example repository, the desktop app's latest release; and the account tools at /mcp/account (OAuth 2.0 from this host, GitHub sign-in): your projects' files, audits, findings and Proofs coverage, and the Mac's swarm, read and steered.
https://formal.team/.well-known/mcp/server-card.jsonSkill: run the local swarm
Download the desktop app, add a Solidity folder, run the agents on your Claude plan or your own key, and Start: the swarm proves each in-scope function in Lean 4 and files bugs with Foundry PoCs, keeping everything in the folder and nothing on GitHub.
https://formal.team/.well-known/agent-skills/run-the-local-swarm/SKILL.mdSkill: read Formal Mind's results
The files Formal Mind keeps in a repository (.formal/, formal/, audit/) and the formalmind.audit/v1 format for audit reports and findings.
https://formal.team/.well-known/agent-skills/read-formal-mind-results/SKILL.mdSkill: connect Formal Mind as an MCP connector
Add formal.team/mcp/account to Claude, ChatGPT or Cursor, sign in with GitHub, and ask about or act on your own account: projects, their audits, findings and Proofs coverage, and the swarm in the desktop app, read and steered.
https://formal.team/.well-known/agent-skills/connect-formal-mind-as-mcp/SKILL.mdSkill: onboard a repository
Plan a Solidity repository, add it as a project (a local folder or a remote repository) with its Code, Bugs and Proofs tabs, and optionally set up specs built from its commits.
https://formal.team/.well-known/agent-skills/onboard-a-repository/SKILL.mdFormal Mind full reference for agents
What Formal Mind is, how the local swarm works and where it keeps its files, what an agent can do here today, and what is planned.
https://formal.team/llms-full.txtAnd 3 more entries in the catalog, not shown here.
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Protocol
- mcp
- Version
- 0.4.0
View all card details
- Capabilities
- tools
- Agent card
- https://formal.team/mcp
Operate this agent and would rather not be listed? Request removal.