com.fidacy/ai-agent-firewall
NPM · @FIDACY/MCP · SCANNED SEP 21
Every agent action watched, every money-moving one gated, every verdict independently verifiable.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security86
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Install-script check failed: the install command fetches or executes arbitrary code (inline_eval). An install hook runs on every machine, in CI, and on transitive installs, whether or not you ever run the server. View diagnostics → Fail
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 12 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability74
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1535 tokens (~127/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage86
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 52% of tool parameters carry a description.Partial
- Structured output schemas are declared (17% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the com.fidacy/ai-agent-firewall MCP server?
com.fidacy/ai-agent-firewall runs locally as an npm package, launched with npx -y @fidacy/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @fidacy/mcp
claude mcp add com-fidacy-ai-agent-firewall -- npx -y @fidacy/mcp
{
"mcpServers": {
"com-fidacy-ai-agent-firewall": {
"command": "npx",
"args": [
"-y",
"@fidacy/mcp"
]
}
}
} {
"servers": {
"com-fidacy-ai-agent-firewall": {
"command": "npx",
"args": [
"-y",
"@fidacy/mcp"
]
}
}
} codex mcp add com-fidacy-ai-agent-firewall -- npx -y @fidacy/mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-fidacy-ai-agent-firewall": {
"type": "local",
"command": [
"npx",
"-y",
"@fidacy/mcp"
],
"enabled": true
}
}
} openclaw mcp add com-fidacy-ai-agent-firewall --command npx --arg -y --arg @fidacy/mcp
mcp_servers:
com-fidacy-ai-agent-firewall:
command: "npx"
args: ["-y", "@fidacy/mcp"] {
"McpServers": {
"com-fidacy-ai-agent-firewall": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@fidacy/mcp"
]
}
}
} assistant mcp add com-fidacy-ai-agent-firewall -t stdio -c npx -a -y @fidacy/mcp
{
"mcpServers": {
"com-fidacy-ai-agent-firewall": {
"command": "npx",
"args": [
"-y",
"@fidacy/mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 −3
- Stability: pass → 0.77 functional
- 16 Sept 26 0
- Stability: 0.97 → pass security
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −2
- Stability: pass → 0.83 functional
- 10 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Sept 2026 · Analysed npm/@fidacy/mcp@0.7.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| postinstall | dangerous | node -e "try{require('fs').accessSync('dist/postinstall.js')}catch{process.exit(0)};import('./dist/postinstall.js')" || exit 0 |
Background: Why install scripts are a supply-chain risk →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
anchor_artifact Anchor Artifact (Bitcoin-anchored integrity proof) ~185
Prove an artifact existed exactly as-is at this moment, and make any later tampering detectable. Give a file `path` (hashed locally with SHA-256 — the file itself is NEVER uploaded) or a precomputed `sha256`. The hash is registered on Fidacy's tamper-evident audit chain, which is checkpointed to the Bitcoin blockchain, and you get a signed receipt (JWS) verifiable offline against the engine JWKS. Use it for contracts, invoices, medical prescriptions, insurance claims, images, audio, video. `kind` defaults to document; optional `label` is a short reference (an invoice number, a case id — no PII).
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | – | – |
| label | string | – | – |
| path | string | – | – |
| sha256 | string | – | – |
| subject | string | – | – |
No output schema declared.
No examples provided.
assess_action Assess Action (Signed Trust Verdict) ~195
Return a SIGNED Fidacy trust verdict from the live engine (default https://api.fidacy.com) for a proposed action. The signed proof is `riskPayloadJws` + `signingKeyId`, verifiable by anyone via @fidacy/verify against the engine JWKS at /.well-known/jwks.json. `kind` is one of ap2_payment, message_send, voice_call, custom, claim_document; `mandate` is the action/mandate object for that kind. This is the verdict (advisory) layer and moves no money; it complements the payment-firewall tools (request_payment et al.) in the same install.
| Name | Type | Req | Description |
|---|---|---|---|
| a2a | object | – | – |
| idempotencyKey | string | – | – |
| kind | string | – | – |
| mandate | object | yes | – |
| mandateType | string | – | – |
| spendingMandate | object | – | – |
No output schema declared.
No examples provided.
check_artifact Check Artifact (was this hash anchored?) ~94
Check whether an artifact was anchored by this account and the state of its Bitcoin checkpoint. Give a file `path` (hashed locally, never uploaded) or a `sha256`. If the current hash of a file does NOT match any anchored record that you expected to match, the file changed since anchoring — that is exactly the tampering signal.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | – | – |
| sha256 | string | – | – |
No output schema declared.
No examples provided.
explain_decision Explain a Decision (why was this allowed or blocked) ~72
Explain one decision in plain language: what was requested, what the mandate did about it, why, and the tamper-evident proof for it. Use when an operator asks why a specific payment was blocked.
| Name | Type | Req | Description |
|---|---|---|---|
| decisionId | string | yes | Decision id from request_payment, list_decisions or spend_summary |
No output schema declared.
No examples provided.
get_audit_proof Get Audit Proof ~56
Return the tamper-evident, hash-chained proof for a decision id, including whether the chain is intact and the public key it verifies against.
| Name | Type | Req | Description |
|---|---|---|---|
| decisionId | string | yes | Decision id returned by request_payment |
No output schema declared.
No examples provided.
list_decisions List Recent Payment Decisions ~87
List recent agent payment decisions, newest first, with payee, amount, the agent's stated reason, and for blocked ones the rule that stopped it. Filter by status to answer 'what got blocked' directly. Read-only, works offline.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many decisions to return. Default 20. |
| status | string | – | Filter by outcome. Default all. |
No output schema declared.
No examples provided.
register_email Register operator email (opt-in) ~83
Register the operator's email so their agent's protection history can attach to a real Fidacy account and Fidacy can reach them. ONLY call this when the human operator has explicitly given their email and agreed to be contacted — it is consent-based. Does not create an account or move money.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | The operator's email, exactly as they gave it. |
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | – |
| registered | boolean | yes | – |
No examples provided.
request_payment Request Payment Authorization ~272
Authorize a payment action against the active Fidacy mandate. Returns an ALLOW with a signed grant, or a DENY with the violated rule. The downstream executor MUST require the grant. Call this before any payment; never pay without it.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | yes | Amount in the mandate currency |
| category | string | yes | Purpose category (must be allowed by the mandate) |
| currency | string | yes | ISO 4217 currency code |
| idempotencyKey | string | – | Optional. Your own key for this payment, if you have one (an order id, a job id). Leave it out and Fidacy derives one from the payment itself, which is the safer default: a retry of the SAME payment… |
| invoiceRef | string | – | Optional invoice identity. When set, Fidacy enforces one payment per invoice: a second request for the same invoiceRef is DENIED, at any amount. |
| payee | string | yes | Payee identifier |
| purpose | string | yes | Your stated reason for this payment, in your own words. It is persisted readably on the tamper-evident audit record (ALLOW and DENY alike) and becomes part of the after-the-fact proof, so write the r… |
| Name | Type | Req | Description |
|---|---|---|---|
| decisionId | string | yes | – |
| grant | string | – | – |
| message | string | yes | – |
| status | string | yes | – |
| violatedRule | string | – | – |
No examples provided.
sentinel_alerts Sentinel Alerts (allowed, but outside this agent's pattern) ~98
Predictive pattern alerts from the local audit chain: first-ever payee, amount spikes vs this agent's own history, velocity bursts, payments riding the mandate ceiling, and retries after a denial (the behavior our Model Watch benchmark measures). Deterministic and explainable, no model. Use to answer 'has anything unusual happened' before it becomes a loss.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many flagged decisions to return. Default 20. |
No output schema declared.
No examples provided.
spend_summary Spend Summary (what my agents spent and what was blocked) ~97
Operator report over a time window: how many payment decisions were made, how much was paid and to whom, how much was blocked before executing, and which mandate rules did the blocking. Read-only, works offline against the local audit chain. Use this to answer questions like 'what did my agents spend this week' or 'has anything been blocked'.
| Name | Type | Req | Description |
|---|---|---|---|
| days | integer | – | Window in days, counting back from now. Default 7. |
No output schema declared.
No examples provided.
upgrade Upgrade to a Fidacy account ~49
Start upgrading this local install to a real Fidacy account (server-backed signed verdicts, anchored proof, higher volume). Returns a link to open; your anonymous usage is preserved and migrated to the new account.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
verify_mandate Verify Active Mandate ~41
Return the active mandate envelope (caps, allowed payees/categories, window, revocation) and Fidacy's Ed25519 public key for grant verification.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the com.fidacy/ai-agent-firewall MCP server?
com.fidacy/ai-agent-firewall is an MCP server listed in the public MCP registry as com.fidacy/ai-agent-firewall. Every agent action watched, every money-moving one gated, every verdict independently verifiable. This page covers its npm package (@fidacy/mcp).
Is the com.fidacy/ai-agent-firewall MCP server safe to use?
com.fidacy/ai-agent-firewall scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares an install script we flagged as high risk. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the com.fidacy/ai-agent-firewall MCP server expose?
com.fidacy/ai-agent-firewall exposes 12 tools: request_payment, verify_mandate, get_audit_proof, spend_summary, list_decisions, and 7 more. Their descriptions and schemas cost roughly 1,329 tokens of context every time the server is loaded.
Is the com.fidacy/ai-agent-firewall MCP server still maintained?
com.fidacy/ai-agent-firewall is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the com.fidacy/ai-agent-firewall MCP server under?
com.fidacy/ai-agent-firewall declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.