qed.bot register MCP server
bot.qed/registerqed.botstreamable-httpv0.2.0Scanned
Register of AI claims in mathematics, graded by the evidence behind each. Paid Lean proof checks.
16 tools: 5 change things and 11 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the qed.bot register MCP server can do
The qed.bot register MCP server is published by qed.bot, a domain the MCP Registry verified. It has 16 tools. It can create or change data (5 tools: registry_positions, disclosure, open_problems, benchmarks and 1 more), but cannot delete data. 11 tools only read.
2 tools bring in text other people can write (search_formalisations and check_proof); 1 tool can send data out of your system (check_proof).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 2026, version 0.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
16 tools
Changes things 5Claude Code: ask
benchmarksBenchmarks as sets of statements, with how many members already carry public AI work: a contamination figure rather than a study.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Benchmarks as sets of statements, with how many members already carry public AI work: a contamination figure rather than a study.
Annotations the server declares
- readOnlyHint: true
check_proofHave qed.bot rebuild a Lean file at its commit and read what every theorem in it depends on, under the admission rules every stranger's file is held to.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Have qed.bot rebuild a Lean file at its commit and read what every theorem in it depends on, under the admission rules every stranger's file is held to. Costs one credit, or two for a private check; buy credits and make an API key at https://qed.bot/check, and send it as Authorization: Bearer qed_.... Returns at once with the check queued; call get_check until it is done, which takes minutes. A file already checked in public is returned free, and a check that stops on qed.bot's side is refunded.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
disclosureAnnouncements 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
open_problemsStatements not recorded as solved, most valuable prize first.1 finding
Why it is in this group
- The name "open_problems" says "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "open_problems" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "open_problems" says "open": a word for a change.
Description, as the server wrote it Statements not recorded as solved, most valuable prize first. Use formalised_only to restrict to those a prover could attempt directly.
Annotations the server declares
- readOnlyHint: true
registry_positionsEvery registry's position on one result, this register included, with each one's own label preserved beside the bucket it was placed in.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Every registry's position on one result, this register included, with each one's own label preserved beside the bucket it was placed in.
Annotations the server declares
- readOnlyHint: true
Only reads 11Show 11 read-only tools
compare_registriesResults recorded by more than one registry, and how the positions differ.No findings
Why it is in this group
- The name "compare_registries" says "compare": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
get_checkA paid check's status and verdict, by the id check_proof returned.No findings
Why it is in this group
- The name "get_check" says "get": a word for reading.
Description, as the server wrote it A paid check's status and verdict, by the id check_proof returned. Needs the same API key for a private check.
Annotations the server declares
- readOnlyHint: true
get_formalisationOne 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 bet…No findings
Why it is in this group
- The name "get_formalisation" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
get_statementEverything the register holds about one statement: formalisations, cited proofs, recompilation results, graded claims, relations and aliases.No findings
Why it is in this group
- The name "get_statement" says "get": a word for reading.
Description, as the server wrote it Everything the register holds about one statement: formalisations, cited proofs, recompilation results, graded claims, relations and aliases.
Annotations the server declares
- readOnlyHint: true
get_targetEverything the register holds about one target: the record history with who held each value and when, the graded claims, and any check run here.No findings
Why it is in this group
- The name "get_target" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
list_collectionsThe collections held, with counts of statements, formalisations and AI activity.No findings
Why it is in this group
- The name "list_collections" says "list": a word for reading.
Description, as the server wrote it The collections held, with counts of statements, formalisations and AI activity.
Annotations the server declares
- readOnlyHint: true
list_evaluatorsThe object checkers available, what each establishes, what an artifact must look like, and which targets have been checked with it.No findings
Why it is in this group
- The name "list_evaluators" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
list_systemsTrack record per AI system, computed from recorded claims.No findings
Why it is in this group
- The name "list_systems" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
search_formalisationsEvery 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: thi…Reads text others writeNo findings
Why it is in this group
- The name "search_formalisations" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
search_statementsSearch the register of mathematical statements.No findings
Why it is in this group
- The name "search_statements" says "search": a word for reading.
Description, as the server wrote it Search the register of mathematical statements. Returns summaries with formal status, prizes, and how much AI work is recorded against each.
Annotations the server declares
- readOnlyHint: true
search_targetsSearch 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.No findings
Why it is in this group
- The name "search_targets" says "search": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:18 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://qed.bot/mcp: tools/list returned 16 tools to an anonymous client, including registry_positions (write), disclosure (write), open_problems (write), benchmarks (write), check_proof (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnopen_problems
The server marks "open_problems" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true}; The name "open_problems" says "open": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http register https://qed.bot/mcpclaude mcp add --transport http register https://qed.bot/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__register__search_statements",
"mcp__register__get_statement",
"mcp__register__compare_registries",
"mcp__register__search_formalisations",
"mcp__register__get_formalisation",
"mcp__register__list_evaluators",
"mcp__register__search_targets",
"mcp__register__get_target",
"mcp__register__list_collections",
"mcp__register__list_systems",
"mcp__register__get_check"
],
"ask": [
"mcp__register__registry_positions",
"mcp__register__disclosure",
"mcp__register__open_problems",
"mcp__register__benchmarks",
"mcp__register__check_proof"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as register. Review it before you use it.
Capability tags behind 2 rules
- mcp__register__search_formalisations untrusted-input
- mcp__register__check_proof untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/bot.qed/register/verify?hash=a0d8bb57bf5fe53940284ee82452ddf566ce5df33dba77a9eb6da7056f3dc755" | jq -e '.changed == false'Pinned hash a0d8bb57bf5f, from Nov 21, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/bot.qed/register/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/bot.qed/register)Source: MCP Registry. Synced Nov 21, 2026, 13:17 UTC.
qed.bot register MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the qed.bot register MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 5 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the qed.bot register MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the qed.bot register MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the qed.bot register MCP server have?
- 16 tools: 5 write, 11 read. registry_positions, disclosure, open_problems, benchmarks, check_proof, search_statements, get_statement, compare_registries and 8 more.
Does the qed.bot register MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the qed.bot register MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_proof.
Has the qed.bot register MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.