RCO Records - Record of Cleared Orders
io.github.allooloo/rco-recordsallooloostreamable-httpv2.3.0Scanned
The record of what the agent relied on: a signed, chained receipt per cleared read. Verify by id.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 1
- 1 finding
Anlyon alternative
3 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →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.
5 tools
Changes things 3Claude Code: ask
get_statementA signed statement of your slice for a month (month: YYYY-MM) or a date range (from, to: YYYY-MM-DD, to exclusive): count, first and last seq, slice digest, the chain tip at issue,…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "get_statement" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "get_statement" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_statement" says "get": a word for reading.
Description, as the server wrote it A signed statement of your slice for a month (month: YYYY-MM) or a date range (from, to: YYYY-MM-DD, to exclusive): count, first and last seq, slice digest, the chain tip at issue, Ed25519 signature by Allooloo. Authorization: Bearer <customer key>.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
issue_auditor_keyIssue a read-only sub-key on your own slice for your auditor (list_receipts and get_statement only).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 Issue a read-only sub-key on your own slice for your auditor (list_receipts and get_statement only). Authorization: Bearer <customer key>. The key value is returned once.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
write_receiptWrite one v1 receipt for a read a gate has cleared.No findings
Why it is in this group
- The name "write_receipt" says "write": a word for a change.
Description, as the server wrote it Write one v1 receipt for a read a gate has cleared. Authenticated: Authorization: Bearer <writer token>. Idempotent on (writer, subject, subject_type, market, rule_version, cleared_at, answer_hash). Returns the receipt.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
list_receiptsYour own receipts only — the rows whose caller is your customer key — by seq range (from_seq, to_seq, after_seq) or date range (from, to: YYYY-MM-DD, to inclusive), limit ≤ 500.No findings
Why it is in this group
- The name "list_receipts" says "list": a word for reading.
Description, as the server wrote it Your own receipts only — the rows whose caller is your customer key — by seq range (from_seq, to_seq, after_seq) or date range (from, to: YYYY-MM-DD, to inclusive), limit ≤ 500. Authorization: Bearer <customer key>. Refuses without a key.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verify_receiptReturn one receipt by id (rco:… for v1, dec_… for v0) with the verification result (hash, id, signature) and the public key (JWK) that checks it.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return one receipt by id (rco:… for v1, dec_… for v0) with the verification result (hash, id, signature) and the public key (JWK) that checks it. Public.
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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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.
Findings
Matches of fixed checks, with the text they matched.
- Warnget_statement
The server marks "get_statement" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_statement" says "get": a word for reading.
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 2.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http rco-records https://mcp.rco-records.ai/mcpclaude mcp add --transport http rco-records https://mcp.rco-records.ai/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__rco-records__verify_receipt",
"mcp__rco-records__list_receipts"
],
"ask": [
"mcp__rco-records__write_receipt",
"mcp__rco-records__get_statement",
"mcp__rco-records__issue_auditor_key"
],
"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 rco-records. Review it before you use it.
Capability tags behind 1 rule
- mcp__rco-records__get_statement 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://anlyon.dev/api/v1/servers/io.github.allooloo/rco-records/verify?hash=0171d114682b771bee0855b6c07c52447daeef27d6ac383ffa46cc748e3f5d96" | jq -e '.changed == false'Pinned hash 0171d114682b, from Oct 30, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/io.github.allooloo/rco-records/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/io.github.allooloo/rco-records)Source: MCP Registry · repository. Synced Oct 30, 2026, 01:17 UTC.