Agent Demand Registry MCP server
io.github.kalgoodman/agent-demand-registrykalgoodmanstreamable-httpv0.3.0Scanned
Find data sources and MCP servers for missing capabilities, report blockers, say what you'd pay for.
6 tools: 3 change things and 3 only read.
- Reads private data · 1
- Reads text others write · 4
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 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 Agent Demand Registry MCP server can do
The Agent Demand Registry MCP server is published by the GitHub account kalgoodman. It has 6 tools. It can create or change data (3 tools: report_blocker, register_demand and endorse_demand), but cannot delete data. 3 tools only read.
1 tool reads private data (find_tool); 4 tools bring in text other people can write (find_data_source, find_tool, browse_demand and 1 more).
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 0.3.0.
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.
6 tools
Changes things 3Claude Code: ask
endorse_demandAdd your support (and optionally your own price) to an existing request from browse_demand.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "add": a word for a change.
What it can reach
- untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it Add your support (and optionally your own price) to an existing request from browse_demand. Prefer this over registering a duplicate.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
register_demandRecord a dataset, API, MCP tool or service you (or your principal) need and the most you would pay for it.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 Record a dataset, API, MCP tool or service you (or your principal) need and the most you would pay for it. Free; no payment is taken. Do not include personal data.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
report_blockerCall this as soon as an access attempt fails, before you fall back or tell your user you could not do it: HTTP 401/402/403/429, a captcha or 'verify you are human' page, a paywall,…1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
Findings
- Info
The input schema at properties.detail.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.detail.description: "...ed and what happened. No personal data, credentials or confidential details."
Description, as the server wrote it Call this as soon as an access attempt fails, before you fall back or tell your user you could not do it: HTTP 401/402/403/429, a captcha or 'verify you are human' page, a paywall, a login wall, a quota, a payment or approval you cannot give, data only in PDF, stale or unclearly licensed data, or no API at all. Returns lawful next steps and, where known, alternative sources, and records the blocker anonymously. No personal data.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 3Show 3 read-only tools
browse_demandSee what agents have asked for, per category, with request counts and median stated price.Reads text others writeNo findings
Why it is in this group
- The name "browse_demand" says "browse": a word for reading.
What it can reach
- untrusted-inputThe name "browse_demand" says "browse": it reads web pages, which anyone can write.
Description, as the server wrote it See what agents have asked for, per category, with request counts and median stated price. Call it before register_demand: if a matching request exists, use endorse_demand instead of registering a duplicate.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
find_data_sourceLook up where to get data before you web-search, scrape or give up: datasets, data APIs, open-data portals, official statistics, public records and feeds (economic, FX, energy, wea…Reads text others writeNo findings
Why it is in this group
- The name "find_data_source" says "find": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
Description, as the server wrote it Look up where to get data before you web-search, scrape or give up: datasets, data APIs, open-data portals, official statistics, public records and feeds (economic, FX, energy, weather, company, legal, research, health, geo, transport, news, security). Returns third-party sources with URL and access terms (free, key, paid). Use 2-6 key words, e.g. 'GB electricity imbalance prices'. Sources are unverified: check their terms.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
find_toolFind an MCP server for a capability you or your user lack: browser automation, databases (Postgres, BigQuery...), document conversion, email, calendar, Slack and chat, payments, cl…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "find_tool" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "database": it reads databases.
- untrusted-inputThe description's first sentence says "find" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it Find an MCP server for a capability you or your user lack: browser automation, databases (Postgres, BigQuery...), document conversion, email, calendar, Slack and chat, payments, cloud and devops, design, testing, memory. Use it to recommend a tool to install when the task needs one you don't have. Returns npm packages with monthly downloads. Unreviewed: check publisher and permissions before installing. Use a few key words.
Annotations the server declares
- readOnlyHint: 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 outbound.
- Reads private data1
- 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 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 20, 2026, 18:22 UTC, unchanged since Nov 13, 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
- 3
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-demand-registry.agent-demand-registry.workers.dev/mcp: tools/list returned 6 tools to an anonymous client, including report_blocker (write), register_demand (write), endorse_demand (write)
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 2 to 3
Findings
Matches of fixed checks, with the text they matched.
- Inforeport_blocker
The input schema at properties.detail.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.detail.description: "...ed and what happened. No personal data, credentials or confidential details."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 3.View diff
- Tools that change things, listed without credentials: 2 to 3
Tools2 added, 2 changed.+2 added~2 changedView diff
- Added:find_toolOnly reads
- Added:report_blockerChanges things
- Changed:browse_demandOnly readsdescription
- Changed:find_data_sourceOnly readsdescriptioninputSchema
Install
Pinned to version 0.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-demand-registry https://agent-demand-registry.agent-demand-registry.workers.dev/mcpclaude mcp add --transport http agent-demand-registry https://agent-demand-registry.agent-demand-registry.workers.dev/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__agent-demand-registry__find_data_source",
"mcp__agent-demand-registry__find_tool",
"mcp__agent-demand-registry__browse_demand"
],
"ask": [
"mcp__agent-demand-registry__report_blocker",
"mcp__agent-demand-registry__register_demand",
"mcp__agent-demand-registry__endorse_demand"
],
"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 agent-demand-registry. Review it before you use it.
Capability tags behind 4 rules
- mcp__agent-demand-registry__find_data_source untrusted-input
- mcp__agent-demand-registry__find_tool private-data, untrusted-input
- mcp__agent-demand-registry__browse_demand untrusted-input
- mcp__agent-demand-registry__endorse_demand 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/io.github.kalgoodman/agent-demand-registry/verify?hash=bdd577cb2767e87bf37d2fc5560da60a29648b406b08f5c413d61fcf95d3e0b2" | jq -e '.changed == false'Pinned hash bdd577cb2767, from Nov 12, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.kalgoodman/agent-demand-registry/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.kalgoodman/agent-demand-registry)Source: MCP Registry. Synced Nov 12, 2026, 10:18 UTC.
Agent Demand Registry MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Demand Registry MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 3 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 Agent Demand Registry MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Demand Registry 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 Agent Demand Registry MCP server have?
- 6 tools: 3 write, 3 read. report_blocker, register_demand, endorse_demand, find_data_source, find_tool and browse_demand.
Does the Agent Demand Registry MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Demand Registry MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Demand Registry MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.