Signal Desk by LarryBuildsAI
io.github.LarryLemonBot/signal-deskLarryLemonBotstreamable-httpv0.1.3Scanned
One-to-three-cent spend routing, lead research, token-risk, and agent-tool comparison preflights.
4 tools: 2 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
Anlyon alternative
2 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.
4 tools
Changes things 2Claude Code: ask
generate_public_lead_briefFetch a public website and return a buyer-fit brief with public signals, agentic offer angles, and next actions.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "generate_public_lead_brief" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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.
Findings
- Warn
The server marks "generate_public_lead_brief" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_public_lead_brief" says "generate": a word for a change.
Description, as the server wrote it Fetch a public website and return a buyer-fit brief with public signals, agentic offer angles, and next actions. No private contact database is queried. Buy and run for 0.03 USDC on Base at https://payanagent.com/x402/kh7b6yxnq209169aq8wavbqzh98ag9gv.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Public Lead Brief
quote_agent_routeEstimate the cheapest sensible agent execution lane before buying model calls or xpay tools.Reads text others writeNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Estimate the cheapest sensible agent execution lane before buying model calls or xpay tools. Returns a budget decision, tool-stack recommendation, and fallback plan. Buy and run for 0.03 USDC on Base at https://payanagent.com/x402/kh732rk76r7nv67q1h5223kc9x8agkfx.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Agent Route Quote
Only reads 2Show 2 read-only tools
compare_market_tool_optionsCompare a task against public xpay catalog options and observed high-demand tool patterns before an agent chains several paid tools.Reads text others writeNo findings
Why it is in this group
- The name "compare_market_tool_options" says "compare": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Compare a task against public xpay catalog options and observed high-demand tool patterns before an agent chains several paid tools. Returns competing tool surfaces, Signal Desk countermoves, moat guidance, unsupported claims, and recommended next paid calls. Buy and run for 0.03 USDC on Base at https://payanagent.com/x402/kh79rcw8zvdhssthrvbwa32rtd8ahzww.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Market Tool Comparison
score_defi_token_riskReturn a research-only token risk snapshot from public liquidity, volume, pair-age, volatility, and data availability.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Return a research-only token risk snapshot from public liquidity, volume, pair-age, volatility, and data availability. Does not trade and is not financial advice. Buy and run for 0.01 USDC on Base at https://payanagent.com/x402/kh7eqsawc4t694gf1pxqn5shwn8ah5sw.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: DeFi Token Risk Snapshot
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 write4
- 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 Oct 22, 2026, 15:17 UTC, unchanged since Oct 22, 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
- 2
- Protocol version
- 2024-11-05
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://proofbeforepay.vercel.app/revenue/mcp: tools/list returned 4 tools to an anonymous client, including quote_agent_route (write), generate_public_lead_brief (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "generate_public_lead_brief" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_public_lead_brief" says "generate": 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 0.1.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http signal-desk https://proofbeforepay.vercel.app/revenue/mcpclaude mcp add --transport http signal-desk https://proofbeforepay.vercel.app/revenue/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__signal-desk__score_defi_token_risk",
"mcp__signal-desk__compare_market_tool_options"
],
"ask": [
"mcp__signal-desk__quote_agent_route",
"mcp__signal-desk__generate_public_lead_brief"
],
"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 signal-desk. Review it before you use it.
Capability tags behind 4 rules
- mcp__signal-desk__quote_agent_route untrusted-input
- mcp__signal-desk__generate_public_lead_brief untrusted-input, outbound
- mcp__signal-desk__score_defi_token_risk untrusted-input
- mcp__signal-desk__compare_market_tool_options 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://anlyon.dev/api/v1/servers/io.github.LarryLemonBot/signal-desk/verify?hash=a56325e8984c2ee64bc176a0826180a1d017a2a353e5c35a32f0fdb3dd4a8d8b" | jq -e '.changed == false'Pinned hash a56325e8984c, from Oct 21, 2026, 19:10 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/io.github.LarryLemonBot/signal-desk/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/io.github.LarryLemonBot/signal-desk)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.