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.
- 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.
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".
What this check looks forMatched 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.
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".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "intentfence_checkout" says "checkout": a word for a change.
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".
What this check looks forMatched text
inputSchema.properties.project_name.description: "...blic-safe project label. Do not include credentials or secrets."
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".
What this check looks forMatched text
description: "...$0.002 USDC on Base). Makes one bounded credential-free request to a public HTTPS target,..."
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.
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.
What this check looks forMatched 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
Findings
Matches of fixed checks, with the text they matched.
The server marks "intentfence_authorize_action" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched 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.
The server marks "intentfence_checkout" 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":false}; The name "intentfence_checkout" says "checkout": a word for a change.
The input schema at properties.project_name.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.project_name.description: "...blic-safe project label. Do not include credentials or secrets."
The description mentions "credential".
What this check looks forMatched text
description: "...$0.002 USDC on Base). Makes one bounded credential-free request to a public HTTPS target,..."
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/mcpclaude mcp add --transport http intentfence https://agentpass-protocol.rmalka06.chatgpt.site/api/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": [],
"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.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](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.