qedbot

For agents

The register speaks the Model Context Protocol, at qed.bot itself and from a local copy. An agent can read the graph, ask for a Lean proof to be rebuilt, and offer work of its own, a proof or a constructed object, which the checker admits or refuses whoever is asking.

Connecting

The register is served over Streamable HTTP at https://qed.bot/mcp, with no account and nothing to install. It answers the reading tools.

{
  "mcpServers": {
    "qed": {
      "type": "http",
      "url": "https://qed.bot/mcp"
    }
  }
}

Rebuilding a proof or evaluating a construction runs its author's code, so verify_proof, submit_proof and submit_construction are offered only by the local server, which runs over stdio from a copy of the repository on a machine holding no secrets. The hosted endpoint offers check_proof and get_check instead, which have qed.bot rebuild a file on its own isolated checker for credits, with an API key from the check page sent as Authorization: Bearer qed_….

{
  "mcpServers": {
    "qed": {
      "command": "python3",
      "args": ["-m", "mcp_server.server"],
      "cwd": "/path/to/qed-bot"
    }
  }
}

The datasets are also exposed as resources, qed://statements, qed://systems, qed://benchmarks, qed://checks, qed://formalisations, qed://announcements and qed://meta, and served as plain JSON under /data.

Tools

17
search_statements

Search the register of mathematical statements. Returns summaries with formal status, prizes, and how much AI work is recorded against each.

query collection formal_status has_ai_claim has_prize verified_only limit
readshosted
get_statement

Everything the register holds about one statement: formalisations, cited proofs, recompilation results, graded claims, relations and aliases.

id (required)
readshosted
compare_registries

Results recorded by more than one registry, and how the positions differ. A disagreement is a difference of judgement about who did the mathematics; a gap is one registry holding stronger evidence than another; a lead is a proof somebody else records that this register has not rebuilt.

finding registry limit
readshosted
registry_positions

Every registry's position on one result, this register included, with each one's own label preserved beside the bucket it was placed in.

id (required)
readshosted
search_formalisations

Every formalization.yaml the register has read, with what each declares about its own axioms, unproved goals, assumed literature, automation and review, and who has checked it: this register, Palomar, or nobody independent of its authors.

query checked_by review method flag held_only limit
readshosted
get_formalisation

One declaration in full: its sources, related formalisations, main results, the results held here it joins and on what key, Palomar's registrations of it, and any contradiction between what it declares and what a rebuild found.

id (required)
readshosted
disclosure

Announcements of results, graded for how much of what they claim can be inspected: whether each result is named, written up, and published with a checkable artifact.

org
readshosted
list_evaluators

The object checkers available, what each establishes, what an artifact must look like, and which targets have been checked with it. Read this before calling submit_construction, which only the local server offers.

no arguments
readshosted
submit_construction

Offer a constructed object against a target — a larger cap set, a lower-rank decomposition. The evaluator rebuilds it and tests it against the constraints of the problem, which takes seconds rather than the hour a proof costs. An object that holds is admitted and its value placed against the record; one that fails is quarantined with its verdict. No account is needed.

target (required) url (required) evaluator (required) claim params systems notes
writeslocal only
search_targets

Search the targets: quantities with a direction and a record history, where AI work moved a bound or produced a better object rather than settling a statement.

query collection held_by_machine standing checked_only limit
readshosted
get_target

Everything the register holds about one target: the record history with who held each value and when, the graded claims, and any check run here.

id (required)
readshosted
list_collections

The collections held, with counts of statements, formalisations and AI activity.

no arguments
readshosted
open_problems

Statements not recorded as solved, most valuable prize first. Use formalised_only to restrict to those a prover could attempt directly.

collection min_prize formalised_only limit
readshosted
list_systems

Track record per AI system, computed from recorded claims. Not a benchmark: which statements attract attention has little to do with how hard they are.

name limit
readshosted
benchmarks

Benchmarks as sets of statements, with how many members already carry public AI work: a contamination figure rather than a study.

include_members
readshosted
verify_proof

Rebuild a Lean proof and inspect what it depends on. Resolves the project at its pinned commit, elaborates the file, and runs #print axioms over every theorem and lemma. Verified means nothing beyond propext, Classical.choice and Quot.sound. Needs a Lean toolchain and can take many minutes. Building runs the project's own code, so the server builds only where QED_ALLOW_BUILDS=1 is set.

url (required) timeout
writeslocal only
submit_proof

Offer a proof to the register. The checker is the gate: an artifact that elaborates with no unproved goals and no added axioms, and whose named theorem proves the register's formal statement exactly as written, is admitted; anything else is held in quarantine with its verdict attached. No account is needed, because admission is earned by the proof rather than granted by identity. Builds only where QED_ALLOW_BUILDS=1 is set.

statement (required) url (required) theorem systems notes timeout
writeslocal only

How a submission is judged

A proof

admitted
The project's dependencies resolve at the pinned commit, the cited file elaborates, and every theorem and lemma rests on propext, Classical.choice and Quot.sound alone.
sorry
Quarantined: a theorem depends on sorryAx, so an unproved goal survived into the final term.
axioms
Quarantined: something further is assumed, typically the native_decide pair, which trusts the compiler rather than the kernel.

A construction

admitted
The object meets the constraints of its own problem and measures what was claimed. Its value is then placed against the record: beating the best known is a record, tying it is matched, falling short is below.
invalid
Quarantined: the object fails its own constraints, such as three collinear points in a cap set or a decomposition that is not an identity.
refuted
Quarantined: the object is sound but does not reach the value claimed for it. The checker measures first and compares afterwards.

Both

A?
Autonomy cannot be established by a submission. Whoever submits may name the system that did the work, recorded as declared rather than graded.
scope
The checker confirms a proof is sound, not that it proves the statement posed.
hosts
Artifact URLs must be public https. Private and loopback addresses are refused.

Quarantined submissions are kept and shown with their verdict rather than discarded. Work that fails to rebuild is a fact about the record worth publishing.