Agent Trust Firewall MCP server
io.github.Benji18sport/agent-trust-firewallBenji18sportstreamable-httpv1.5.0Scanned
Free pre-action policy checks and data cleaning for autonomous AI agents.
5 tools: 2 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 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 Trust Firewall MCP server can do
The Agent Trust Firewall MCP server is published by the GitHub account Benji18sport. It has 5 tools. It can create or change data (2 tools: trust_check_action and trust_clean_data), but cannot delete data. 3 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (annotation-conflict). 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 1.5.0.
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.
5 tools
Changes things 2Claude Code: ask
trust_check_actionEvaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes.1 finding
Why it is in this group
- The description's first verb is "evaluate": 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 "trust_check_action" 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 description's first verb is "evaluate": a word for a change.
Description, as the server wrote it Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks must pass: evidence cannot override an over-budget payment. Set action.type to payment to activate spending checks and pass its amount with remaining_budget; contract applies to data, not action. Use this gate before execution, trust_check_spend for budget alone, or trust_validate_data for structure alone. Enforce BLOCK and fail closed on errors. Source labels are unauthenticated; instruction scanning is a limited phrase heuristic. No action execution, wallet access, policy storage or decision history. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
trust_clean_dataAudit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts.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 Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplication, then required/range checks: keys " a " and "a" collide after trimming. Duplicate removal keeps the first row and skips later-row field checks; missing keys are retained and flagged. REVIEW persists even after repair, so inspect issues before use; [] returns ALLOW. Numeric strings are not converted or range-checked; use trust_validate_data for type enforcement. Only top-level strings are trimmed; inputs are not mutated. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 3Show 3 read-only tools
trust_check_spendCompare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are independent: amount=4, remaining_budget=10, per_transaction_limit=3 returns BLOCK; equality passes. Use one currency/unit, and update remaining_budget in your application after each actual purchase: this tool neither tracks cumulative spending nor converts currencies. Omitting allowed_merchants skips merchant checks; supplying it requires an exact merchant match, and [] blocks all merchants. Use trust_check_action to include evidence or data checks. Enforce BLOCK before paying; this tool never accesses a wallet or executes payment. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
trust_get_capabilitiesDiscover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating.No findings
Why it is in this group
- The name "trust_get_capabilities" says "get": a word for reading.
Description, as the server wrote it Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory endpoint accepts no action, policy or filter arguments; use tools/list for callable schemas and trust_check_action for a verdict. The response explains enforcement and limitations, not stored policy or decision history: rules must accompany each check. Free and unauthenticated, with operational usage metadata recorded but no request-body storage. Re-read after a deployment to detect capability changes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
trust_validate_dataValidate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields.No findings
Why it is in this group
- The name "trust_validate_data" says "validate": a word for reading.
Description, as the server wrote it Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine required:true, type:"integer" and min:1 for a positive mandatory quantity: min alone neither requires a value nor rejects numeric strings. Missing, null or empty optional values skip the other constraints; 0 and false do not. For nested data, fields["order.total"] addresses a leaf; allow_extra:false compares top-level keys, so keep it true for dot-path rules. Use trust_clean_data for transformations or trust_check_action for evidence/spending checks. This validates structure, not facts or provenance. Free, unauthenticated, stateless pilot: rules apply only to this call. Usage metadata is recorded; request bodies are not stored.
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 or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 21, 2026, 19:23 UTC, unchanged since Nov 7, 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
- 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 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://agent-trust-firewall.andrea-vignoni.workers.dev/mcp: tools/list returned 5 tools to an anonymous client, including trust_check_action (write), trust_clean_data (write)
Posture changes
- Nov 7, 2026
- Tools that change things, listed without credentials: 3 to 2
Findings
Matches of fixed checks, with the text they matched.
The server marks "trust_check_action" 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 description's first verb is "evaluate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools5 added, 4 removed.+5 added−4 removedView diff
- Added:trust_check_actionChanges things
- Added:trust_check_spendOnly reads
- Added:trust_clean_dataChanges things
- Added:trust_get_capabilitiesOnly reads
- Added:trust_validate_dataOnly reads
- Removed:data_clean
- Removed:trust_firewall
- Removed:trust_spend_guard
- Removed:trust_validate
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 2.View diff
- Tools that change things, listed without credentials: 3 to 2
Install
Pinned to version 1.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-trust-firewall https://agent-trust-firewall.andrea-vignoni.workers.dev/mcpclaude mcp add --transport http agent-trust-firewall https://agent-trust-firewall.andrea-vignoni.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-trust-firewall__trust_check_spend",
"mcp__agent-trust-firewall__trust_validate_data",
"mcp__agent-trust-firewall__trust_get_capabilities"
],
"ask": [
"mcp__agent-trust-firewall__trust_check_action",
"mcp__agent-trust-firewall__trust_clean_data"
],
"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-trust-firewall. Review it before you use it.
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.Benji18sport/agent-trust-firewall/verify?hash=c5ab9c4f7c5c6b0e382e3b5fd0f26091d15c4b1a3c1fbc083dcad6c77774425c" | jq -e '.changed == false'Pinned hash c5ab9c4f7c5c, from Nov 12, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Benji18sport/agent-trust-firewall/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Benji18sport/agent-trust-firewall)Source: MCP Registry · repository. Synced Oct 30, 2026, 19:17 UTC.
Agent Trust Firewall MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Trust Firewall MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 2 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 Trust 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 Agent Trust Firewall 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 Trust Firewall MCP server have?
- 5 tools: 2 write, 3 read. trust_check_action, trust_clean_data, trust_check_spend, trust_validate_data and trust_get_capabilities.
Does the Agent Trust Firewall MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Trust Firewall 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 Trust Firewall 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.