Skip to content

IntentFence Agent Action Firewall MCP server

io.github.razel369/intentfencerazel369streamable-httpv0.16.0Scanned

Fail-closed action authorization, MCP risk scanning, x402 checks, and signed receipts.

10 tools: 1 do something that can't be undone and 9 change things.

Tools: 0 delete, 1 irreversible, 9 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 6
  • Can send data out · 2
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • 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 IntentFence Agent Action Firewall MCP server can do

The IntentFence Agent Action Firewall MCP server is published by the GitHub account razel369. It has 10 tools. It can do things that cannot be undone, such as sending, paying or publishing (intentfence_authorize_action) and create or change data (9 tools: intentfence_agent_risk_scan, intentfence_checkout, intentfence_preflight, intentfence_policy_pack and 5 more), but cannot delete data. None of its tools only reads.

6 tools bring in text other people can write (intentfence_policy_pack, intentfence_verified_preflight, intentfence_x402_assessment and 3 more); 2 tools can send data out of your system (intentfence_x402_assessment and intentfence_x402_readiness).

The fixed checks matched 4 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 21, 2026, version 0.16.0.

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.

10 tools

Can't be undone 1Claude Code: ask
  • intentfence_authorize_actionAuthorize an exact agent action against an explicit allowlist, spend ceiling, retention ceiling, and optional action-bound approval.1 finding

    Why it is in this group

    • The input carries an amount (input.policy.max_cost.amount) and a currency, so it moves money.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "intentfence_authorize_action" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The input carries an amount (input.policy.max_cost.amount) and a currency, so it moves money.

      What this check looks for
    Description, as the server wrote it
    Authorize an exact agent action against an explicit allowlist, spend ceiling, retention ceiling, and optional action-bound approval. Returns a five-minute ES256 receipt and never executes the downstream action. Callers must verify the receipt and fail closed if the action changes.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 9Claude Code: ask
  • intentfence_agent_risk_scanFree metadata-only scan of caller-supplied MCP tool definitions for missing schemas, unsafe annotations, approval binding, and cost boundaries.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 metadata-only scan of caller-supplied MCP tool definitions for missing schemas, unsafe annotations, approval binding, and cost boundaries. Does not execute tools or certify security.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • intentfence_checkoutFree machine checkout builder.1 finding

    Why it is in this group

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

      Matched text

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

      What this check looks for
    Description, as the server wrote it
    Free machine checkout builder. Select a paid IntentFence outcome and receive the exact endpoint, validated request, USDC cap, shell-safe Agentic Wallet argv, MCP tool call, and opt-in local auto-payment budget. It never signs or initiates payment.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • intentfence_policy_packPaid self-service integration pack (1 USDC on Base).Reads text others write1 finding

    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.

    Findings

    • Info

      The input schema at properties.project_name.description mentions "credentials".

      Matched text

      inputSchema.properties.project_name.description: "...blic-safe project label. Do not include credentials or secrets."

      What this check looks for
    Description, as the server wrote it
    Paid self-service integration pack (1 USDC on Base). Generates a runtime-specific TypeScript guard, signed action and policy receipt, negative test vectors, and a fail-closed deployment checklist for Cloudflare Agents, Coinbase AgentKit, or an MCP gateway. No meeting or account is required.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • intentfence_preflightFree declared-input preview with no signed receipt, authorization proof, or enforcement guarantee.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 declared-input preview with no signed receipt, authorization proof, or enforcement guarantee. Returns safe_to_proceed, needs_review, or denied.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • intentfence_us_cpiPaid official U.S.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
    Paid official U.S. CPI and core CPI data ($0.001 USDC on Base), retrieved from the Bureau of Labor Statistics with a six-hour edge cache and returned with an ES256 provenance receipt. Optionally request a YYYY-MM period.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • intentfence_verified_preflightPaid production preflight ($0.005 USDC on Base).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
    Paid production preflight ($0.005 USDC on Base). Settles through x402 and returns a signed ES256 audit receipt plus settlement metadata.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • intentfence_wallet_riskPaid AML/KYT wallet screening ($0.002 USDC on Base) before sending funds or approving a transaction.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
    Paid AML/KYT wallet screening ($0.002 USDC on Base) before sending funds or approving a transaction. Checks live Base activity plus GoPlus sanctions, phishing, mixer, money-laundering, dark-web, blacklist, and related counterparty-risk flags, then returns a five-minute ES256 receipt. A low-risk result is not proof of identity, ownership, authorization, or future behavior.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • intentfence_x402_assessmentPaid assessment ($0.005 USDC on Base).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.target_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Paid assessment ($0.005 USDC on Base). Forward the exact base64 or base64url PAYMENT-REQUIRED header observed by the caller. IntentFence validates the quote, canonical Base USDC asset, price ceiling, payee allowlist, timeout, and resource binding without contacting the target, then returns a short-lived ES256 receipt bound to the quote hash. Supply allowed_payees for safe_to_proceed; omission yields needs_review.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • intentfence_x402_readinessPaid live endpoint check ($0.002 USDC on Base).Reads text others writeCan send data out1 finding

    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.target_url): a request to a URL can carry data to whoever runs it.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...$0.002 USDC on Base). Makes one bounded credential-free request to a public HTTPS target,..."

      What this check looks for
    Description, as the server wrote it
    Paid live endpoint check ($0.002 USDC on Base). Makes one bounded credential-free request to a public HTTPS target, blocks private networks and redirects, never pays the target, validates the returned x402 challenge, and returns a signed five-minute receipt.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true

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 write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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, 19:26 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
10
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 10 tools that change things (1 irreversible, 9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agentpass-protocol.rmalka06.chatgpt.site/api/mcp: tools/list returned 10 tools to an anonymous client, including intentfence_authorize_action (irreversible), intentfence_agent_risk_scan (write), intentfence_checkout (write), intentfence_preflight (write), intentfence_policy_pack (write) and 5 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn2 info
  • The server marks "intentfence_authorize_action" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The input carries an amount (input.policy.max_cost.amount) and a currency, so it moves money.

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

    Matched text

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

    What this check looks for
  • The input schema at properties.project_name.description mentions "credentials".

    Matched text

    inputSchema.properties.project_name.description: "...blic-safe project label. Do not include credentials or secrets."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...$0.002 USDC on Base). Makes one bounded credential-free request to a public HTTPS target,..."

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

claude mcp add --transport http intentfence https://agentpass-protocol.rmalka06.chatgpt.site/api/mcp
claude mcp add --transport http intentfence https://agentpass-protocol.rmalka06.chatgpt.site/api/mcp

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": [],
    "ask": [
      "mcp__intentfence__intentfence_authorize_action",
      "mcp__intentfence__intentfence_agent_risk_scan",
      "mcp__intentfence__intentfence_checkout",
      "mcp__intentfence__intentfence_preflight",
      "mcp__intentfence__intentfence_policy_pack",
      "mcp__intentfence__intentfence_verified_preflight",
      "mcp__intentfence__intentfence_x402_assessment",
      "mcp__intentfence__intentfence_x402_readiness",
      "mcp__intentfence__intentfence_wallet_risk",
      "mcp__intentfence__intentfence_us_cpi"
    ],
    "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 intentfence. Review it before you use it.

Capability tags behind 6 rules
  • mcp__intentfence__intentfence_policy_pack untrusted-input
  • mcp__intentfence__intentfence_verified_preflight untrusted-input
  • mcp__intentfence__intentfence_x402_assessment untrusted-input, outbound
  • mcp__intentfence__intentfence_x402_readiness untrusted-input, outbound
  • mcp__intentfence__intentfence_wallet_risk untrusted-input
  • mcp__intentfence__intentfence_us_cpi 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.razel369/intentfence/verify?hash=ac5c71bfd660102cd159b0eb03572508e5cba45c372628681a4b61f425bc364c" | jq -e '.changed == false'

Pinned hash ac5c71bfd660, from Nov 21, 2026, 16:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.razel369/intentfence/changes.xml

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

Badge

Anlyon Radar badge for io.github.razel369/intentfence
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.razel369/intentfence.svg)](https://radar.anlyon.com/servers/io.github.razel369/intentfence)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:45 UTC.

IntentFence Agent Action Firewall MCP server: questions and answers

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

Is the IntentFence Agent Action Firewall MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 10 of which can change, send or delete something, and 4 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 IntentFence Agent Action Firewall MCP server delete data?

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

Can the IntentFence Agent Action Firewall MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: intentfence_authorize_action.

What tools does the IntentFence Agent Action Firewall MCP server have?

10 tools: 1 irreversible, 9 write. intentfence_authorize_action, intentfence_agent_risk_scan, intentfence_checkout, intentfence_preflight, intentfence_policy_pack, intentfence_verified_preflight, intentfence_x402_assessment, intentfence_x402_readiness and 2 more.

Does the IntentFence Agent Action Firewall MCP server need sign-in or OAuth?

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

Does the IntentFence Agent Action Firewall MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): intentfence_x402_assessment and intentfence_x402_readiness.

Has the IntentFence Agent Action Firewall MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.