Skip to content

H/M Agent Surface - Free MCP Tools

net.hogarmas/agent-surfacehogarmas.netstreamable-httpv1.8.0Scanned

Five free MCP tools, including proof-before-payment preview, plus one authorized x402 pack.

7 tools: 4 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 4 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 3
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

4 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.
Govern this server →

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 H/M Agent Surface - Free MCP Tools can do

The H/M Agent Surface - Free MCP Tools is published by hogarmas.net, a domain the MCP Registry verified. It has 7 tools. It can create or change data (4 tools: lint_mcp_activation, create_mcp_connection_receipt, audit_agent_surface and unlock_agent_surface_evidence_pack), but cannot delete data. 3 tools only read.

4 tools bring in text other people can write (audit_agent_surface, compare_mcp_registry_releases, preview_agent_surface_evidence_pack and 1 more); 3 tools can send data out of your system (audit_agent_surface, preview_agent_surface_evidence_pack and unlock_agent_surface_evidence_pack).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 18, 2026, version 1.8.0.

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.

7 tools

Changes things 4Claude Code: ask
  • audit_agent_surfaceChecks nine named ChatGPT, Claude, Perplexity and Google crawler controls by search, user-retrieval and training purpose, then maps observed evidence into discover, understand, tru…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.
    • 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.
    Description, as the server wrote it
    Checks nine named ChatGPT, Claude, Perplexity and Google crawler controls by search, user-retrieval and training purpose, then maps observed evidence into discover, understand, trust, act and pay stages. Returns structured evidence, the first evidence gap and an unsigned checksum share receipt. Free, no authentication. It does not observe a real buyer session or test checkout; the target and response bodies are not stored.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • create_mcp_connection_receiptZero-input end-to-end tool-call preflight.1 finding

    Why it is in this group

    • The name "create_mcp_connection_receipt" says "create": 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 "create_mcp_connection_receipt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "create_mcp_connection_receipt" says "create": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Zero-input end-to-end tool-call preflight. Returns a browser-verifiable SHA-256 receipt for this named tools/call, the current focused server contract and exact free next actions. No authentication or target required. The detached receipt is unsigned, does not verify client identity and is not certification.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • lint_mcp_activationFree static activation lint for initialize and tools/list metadata.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
    Free static activation lint for initialize and tools/list metadata. With no input it inspects this focused server. Returns five evidence stages, the first friction point and deterministic remediation. It stores no supplied metadata, executes no tool, predicts no conversion and produces no security or compliance verdict.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • unlock_agent_surface_evidence_packRuns a live public-surface audit after exact x402 settlement and returns resource SHA-256 digests, selected HTTP headers, deterministic remediation templates and an unsigned packag…Reads text others writeCan send data out1 finding

    Why it is in this group

    • The name "unlock_agent_surface_evidence_pack" says "unlock": 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 "unlock_agent_surface_evidence_pack" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "unlock_agent_surface_evidence_pack" says "unlock": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Runs a live public-surface audit after exact x402 settlement and returns resource SHA-256 digests, selected HTTP headers, deterministic remediation templates and an unsigned package integrity receipt. It does not certify identity, ranking, indexing or citation.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • compare_mcp_registry_releasesZero-input Release Signal for H/M Agent Surface, or an official MCP Registry preview comparison for a supplied server name.Reads text others writeNo findings

    Why it is in this group

    • The name "compare_mcp_registry_releases" 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
    Zero-input Release Signal for H/M Agent Surface, or an official MCP Registry preview comparison for a supplied server name. Compares explicit versions or the latest two, returns structured drift evidence and an unsigned SHA-256 receipt. Free, read-only and no authentication. It never fetches or executes packages, never returns secret values and is not a security or compatibility verdict.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_mcp_handshake_observatoryReturns a privacy-minimized aggregate of MCP initialize handshakes, named tool requests, client classes, protocol versions and declared capabilities observed by H/M endpoints.No findings

    Why it is in this group

    • The name "get_mcp_handshake_observatory" says "get": a word for reading.
    Description, as the server wrote it
    Returns a privacy-minimized aggregate of MCP initialize handshakes, named tool requests, client classes, protocol versions and declared capabilities observed by H/M endpoints. Free, no authentication and no input required. A handshake is not proof of an AI user; clientInfo is self-declared and QA is excluded.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • preview_agent_surface_evidence_packReturns the exact free-versus-paid delta, current public x402 terms, expected evidence inventory, fit criteria and an unsigned checksum.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "preview_agent_surface_evidence_pack" says "preview": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Returns the exact free-versus-paid delta, current public x402 terms, expected evidence inventory, fit criteria and an unsigned checksum. No input is required; an optional public website only scopes the preview. It does not fetch the target, attempt payment or include the paid artifact.

    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 write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:16 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
4
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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agents.hogarmas.net/mcp/agent-surface: tools/list returned 7 tools to an anonymous client, including lint_mcp_activation (write), create_mcp_connection_receipt (write), audit_agent_surface (write), unlock_agent_surface_evidence_pack (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "create_mcp_connection_receipt" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "create_mcp_connection_receipt" says "create": a word for a change.

    What this check looks for
  • The server marks "unlock_agent_surface_evidence_pack" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "unlock_agent_surface_evidence_pack" says "unlock": a word for a change.

    What this check looks for

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 1.8.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-surface https://agents.hogarmas.net/mcp/agent-surface
claude mcp add --transport http agent-surface https://agents.hogarmas.net/mcp/agent-surface

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-surface__compare_mcp_registry_releases",
      "mcp__agent-surface__get_mcp_handshake_observatory"
    ],
    "ask": [
      "mcp__agent-surface__lint_mcp_activation",
      "mcp__agent-surface__create_mcp_connection_receipt",
      "mcp__agent-surface__audit_agent_surface",
      "mcp__agent-surface__preview_agent_surface_evidence_pack",
      "mcp__agent-surface__unlock_agent_surface_evidence_pack"
    ],
    "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-surface. Review it before you use it.

Capability tags behind 4 rules
  • mcp__agent-surface__audit_agent_surface untrusted-input, outbound
  • mcp__agent-surface__compare_mcp_registry_releases untrusted-input
  • mcp__agent-surface__preview_agent_surface_evidence_pack untrusted-input, outbound
  • mcp__agent-surface__unlock_agent_surface_evidence_pack 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/net.hogarmas/agent-surface/verify?hash=130e602c56d311111e84ab133c371ac49782d9d4bfcde426a0c49882d7d84d26" | jq -e '.changed == false'

Pinned hash 130e602c56d3, from Nov 18, 2026, 20:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/net.hogarmas/agent-surface/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for net.hogarmas/agent-surface
[![Anlyon Radar](https://radar.anlyon.com/badge/net.hogarmas/agent-surface.svg)](https://radar.anlyon.com/servers/net.hogarmas/agent-surface)

Source: MCP Registry. Synced Oct 21, 2026, 18:53 UTC.

H/M Agent Surface - Free MCP Tools: questions and answers

Answered from the scan above, not from the publisher's description.

Is the H/M Agent Surface - Free MCP Tools safe?

No scan can promise that. What its definitions show: 7 tools, 4 of which can change, send or delete something, and 2 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 H/M Agent Surface - Free MCP Tools delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the H/M Agent Surface - Free MCP Tools 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 H/M Agent Surface - Free MCP Tools have?

7 tools: 4 write, 3 read. lint_mcp_activation, create_mcp_connection_receipt, audit_agent_surface, unlock_agent_surface_evidence_pack, compare_mcp_registry_releases, get_mcp_handshake_observatory and preview_agent_surface_evidence_pack.

Does the H/M Agent Surface - Free MCP Tools need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the H/M Agent Surface - Free MCP Tools send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): audit_agent_surface, preview_agent_surface_evidence_pack and unlock_agent_surface_evidence_pack.

Has the H/M Agent Surface - Free MCP Tools changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.