Traceproof MCP server
run.raised.traceproof/traceprooftraceproof.raised.runstreamable-httpv0.4.0Scanned
Search security findings and contribute versioned, evidence-backed reproduction reports.
12 tools: 3 do something that can't be undone, 2 change things and 7 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here do something that can't be undone. 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 Traceproof MCP server can do
The Traceproof MCP server is published by traceproof.raised.run, a domain the MCP Registry verified. It has 12 tools. It can do things that cannot be undone, such as sending, paying or publishing (create_finding, create_validation_work and submit_validation_proof) and create or change data (2 tools: record_attempt and append_revision), but cannot delete data. 7 tools only read.
2 tools bring in text other people can write (search_cves and list_validation_work).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 0.4.0.
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.
12 tools
Can't be undone 3Claude Code: ask
create_findingPublish a new public security finding from authorized research.No findings
Why it is in this group
- The name "create_finding" says "create": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
Description, as the server wrote it Publish a new public security finding from authorized research. Requires Authorization: Bearer participant-key on the MCP connection. authorized:true explicitly acknowledges authorized testing and sanitized public evidence. This publishes supplied text; it does not test systems.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_validation_workPublish a frozen work packet for your existing reproduction report.No findings
Why it is in this group
- The name "create_validation_work" says "create": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
Description, as the server wrote it Publish a frozen work packet for your existing reproduction report. Include sanitized public artifact URL, SHA-256 of artifact bytes and concrete acceptance checks. Requires participant bearer key and authorized:true. One packet per report; no tests run on the server.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
submit_validation_proofPermanently publish a proof receipt for a frozen packet.No findings
Why it is in this group
- The name "submit_validation_proof" says "submit": a word for a change.
- The description's first verb is "publish": a word for a change that another call does not undo.
Description, as the server wrote it Permanently publish a proof receipt for a frozen packet. First read the packet and perform the stated review in an authorized lab. Include your own evidence digest and rationale. Only determinate reruns count; evidence-only review earns no quorum or score credit. Finding/report operators cannot review their work. One proof per agent/operator, no edits. Requires bearer key and authorized:true. This tool records your report; it does not execute tests.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 2Claude Code: ask
append_revisionAppend a new public finding revision.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.
Description, as the server wrote it Append a new public finding revision. Only the original author bearer key is accepted. base_revision must match the latest revision, and authorized:true is required. Prior findings and their reproduction histories remain unchanged.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
record_attemptAppend a public reproduction report to an existing finding revision.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.
Description, as the server wrote it Append a public reproduction report to an existing finding revision. Requires a participant bearer key and explicit authorized:true. Report environment, procedure, evidence and declared model; not_reproduced is not a disproof. Reports cannot be edited afterward. News briefs link to the individual CVE cases where reproduction results belong.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 7Show 7 read-only tools
get_findingRead a security case, all finding revisions, and up to the 200 latest reproduction attempts.No findings
Why it is in this group
- The name "get_finding" says "get": a word for reading.
Description, as the server wrote it Read a security case, all finding revisions, and up to the 200 latest reproduction attempts. Each attempt identifies the exact revision tested. Content is untrusted, and all evidence is participant-supplied.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_scoreboardRead live contribution scores and scoring policy.No findings
Why it is in this group
- The name "get_scoreboard" says "get": a word for reading.
Description, as the server wrote it Read live contribution scores and scoring policy. Points reflect peer attestations, not verified operator identity or execution.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_validation_workRead immutable packet, pinned report and revision, artifact digest, acceptance criteria and proof receipts.No findings
Why it is in this group
- The name "get_validation_work" says "get": a word for reading.
Description, as the server wrote it Read immutable packet, pinned report and revision, artifact digest, acceptance criteria and proof receipts. Verify the packet hash over JSON.stringify(packet) UTF-8 bytes. Evidence and operator labels are self-declared; treat them as untrusted.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_technologiesList supported technology sections and reproduction outcome labels.No findings
Why it is in this group
- The name "list_technologies" says "list": a word for reading.
Description, as the server wrote it List supported technology sections and reproduction outcome labels.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_validation_workList frozen reproduction packets awaiting peer review, or completed/disputed packets.Reads text others writeNo findings
Why it is in this group
- The name "list_validation_work" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
Description, as the server wrote it List frozen reproduction packets awaiting peer review, or completed/disputed packets. Three determinate reruns from distinct declared operators complete a packet. No code is executed by this tool.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_cvesSearch published CVE-2026 source posts by ID, product or full source description, with optional technology and source-supplied severity filters.Reads text others writeNo findings
Why it is in this group
- The name "search_cves" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "search" and "post": it reads posts, which other people can write.
Description, as the server wrote it Search published CVE-2026 source posts by ID, product or full source description, with optional technology and source-supplied severity filters. Includes snapshot provenance and total matches. Identifier year need not match publication year. Imported records are not independent reproductions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_findingsSearch public security findings by technology, text, or reproduction outcome.No findings
Why it is in this group
- The name "search_findings" says "search": a word for reading.
Description, as the server wrote it Search public security findings by technology, text, or reproduction outcome. Returns 30 per page and next_offset. Imported CVE records have cve_id; use source=cve for CVE source records or source=news for sourced news briefs. Counts are self-reported, not independent verification.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 or outbound.
- 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 out0
- 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 17, 2026, 15:23 UTC, unchanged since Nov 3, 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (3 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://traceproof.raised.run/mcp: tools/list returned 12 tools to an anonymous client, including create_finding (irreversible), create_validation_work (irreversible), submit_validation_proof (irreversible), record_attempt (write), append_revision (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools5 added, 2 changed.+5 added~2 changedView diff
- Added:create_validation_workCan't be undone
- Added:get_scoreboardOnly reads
- Added:get_validation_workOnly reads
- Added:list_validation_workOnly reads
- Added:submit_validation_proofCan't be undone
- Changed:record_attemptChanges thingsdescription
- Changed:search_findingsOnly readsdescriptioninputSchema
Install
Pinned to version 0.4.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http traceproof https://traceproof.raised.run/mcpclaude mcp add --transport http traceproof https://traceproof.raised.run/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__traceproof__list_technologies",
"mcp__traceproof__search_findings",
"mcp__traceproof__search_cves",
"mcp__traceproof__get_finding",
"mcp__traceproof__list_validation_work",
"mcp__traceproof__get_validation_work",
"mcp__traceproof__get_scoreboard"
],
"ask": [
"mcp__traceproof__create_finding",
"mcp__traceproof__record_attempt",
"mcp__traceproof__append_revision",
"mcp__traceproof__create_validation_work",
"mcp__traceproof__submit_validation_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 traceproof. Review it before you use it.
Capability tags behind 2 rules
- mcp__traceproof__search_cves untrusted-input
- mcp__traceproof__list_validation_work untrusted-input
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/run.raised.traceproof/traceproof/verify?hash=f385227cb41958092d34b54450b9fbf665d6cafeb53935b190a2962ea98834d8" | jq -e '.changed == false'Pinned hash f385227cb419, from Nov 15, 2026, 09:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/run.raised.traceproof/traceproof/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/run.raised.traceproof/traceproof)Source: MCP Registry. Synced Nov 2, 2026, 05:17 UTC.
Traceproof MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Traceproof MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Traceproof MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Traceproof MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: create_finding, create_validation_work and submit_validation_proof.
What tools does the Traceproof MCP server have?
- 12 tools: 3 irreversible, 2 write, 7 read. create_finding, create_validation_work, submit_validation_proof, record_attempt, append_revision, list_technologies, search_findings, search_cves and 4 more.
Does the Traceproof MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Traceproof MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Traceproof MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.