WARDEN by AIMarket — MCP tool firewall
NPM · @AIMARKET/WARDEN
MCP security firewall: stdio wrap proxy or inspection tools; zero runtime dependencies.
Available components
Last scanned (4 hours ago)
Scores higher than 38% of npm servers
Category Security
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 Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency48
- 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 (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3378 tokens (~375/item across 9 items; 9 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% 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
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
- Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (15)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- Security disclosure: unverified → pass ▲ functional
- Package version: 0.33.0 → 0.36.0 functional
- Package version: 0.33.0 → 0.35.0 functional
- 20 Nov 26 −1
- Security disclosure: pass → unverified ▼ functional
- Package version: 0.31.0 → 0.33.0 functional
- 19 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 18 Nov 26 0
- Malware scan: unverified → pass ▲ security
- Package version: 0.29.0 → 0.31.0 functional
- Package version: 0.29.0 → 0.30.0 functional
- 17 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.28.0 → 0.29.0 functional
- 16 Nov 26 +15
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Malware scan: unverified → pass ▲ security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Package version: 0.27.0 → 0.28.0 functional
- 15 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 0.26.1 → 0.27.0 functional
- 13 Nov 26 +1
- 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 Nov 2026 · Analysed npm/@aimarket/warden@0.36.0
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 →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| 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 →
approve_mcp_server Record an operator's approval of an MCP server ~496
Store an operator approval for exactly the tool definitions and launch identity the operator reviewed, so later vet_mcp_server calls treat them as approved and report any change as drift. The server must still pass every WARDEN gate; an approval cannot override a block. When to use: after a human reviewed the output of status_mcp_server and agreed. Pass back the currentToolsHash, currentIdentityHash and previousRevision it returned; if the payload or the stored approval changed in the meantime, the call is refused and the review must be repeated. When NOT to use: on your own initiative or to make a blocked server pass (the gates run again and the call fails); to remove an approval (revoke_mcp_server); to look at the stored state (status_mcp_server). Behaviour: writes one file in the local state directory and replaces any earlier approval for this server id. Refused unless the operator started this process with WARDEN_ALLOW_PIN_CHANGES=1. No network; never starts the target server. Repeating the same call is refused because the revision it names is no longer current. Returns { approved: true, pin }. Example: approve_mcp_server({ server, tools, reviewed_tools_hash: "<currentToolsHash>", reviewed_identity_hash: "<currentIdentityHash>", previous_pin_revision: null }).
| Name | Type | Req | Description |
|---|---|---|---|
| previous_pin_revision | string|null | yes | The previousRevision value status_mcp_server returned when you reviewed this server (null when it reported no stored approval). The write is refused if the stored approval changed since then, so two… |
| reviewed_identity_hash | string | yes | currentIdentityHash from the same status_mcp_server call. |
| reviewed_tools_hash | string | yes | currentToolsHash from the status_mcp_server call the operator reviewed. |
| server | object | yes | Identity of the MCP server being vetted — the host's McpServerRef, not a live connection. WARDEN never launches this command or fetches this URL. |
| server_info | object | – | Optional: the serverInfo object from the server's initialize result, unmodified ({ name, version }). Shown next to the review as the version the server reports, and stored with an approval; it is the… |
| tools | array | yes | The exact tools/list payload the operator reviewed. Its hash must equal reviewed_tools_hash. |
| Name | Type | Req | Description |
|---|---|---|---|
| approved | boolean | yes | Always true; any refusal is returned as an error instead. |
| pin | object | yes | The approval as stored, with approvalMode "operator". |
No examples provided.
canonicalize_json Canonicalize JSON with RFC 8785 (JCS) bytes ~282
Return the RFC 8785 JSON Canonicalization Scheme serialization WARDEN uses for threat-feed signatures and tool-def pins, so another implementation can byte-check against it. Integers only inside ±(2^53−1); lone surrogates and non-integers are refused with a reason code, not escaped. When to use: you are publishing or verifying a signed threat feed, hashing tool defs, or comparing two JSON documents that must agree regardless of key order. Subpath @aimarket/warden/jcs is the same function. When NOT to use: scanning tool defs (static_scan_tools); pretty-printing for humans (this output is for bytes, not display). Behaviour: local, no network. Pass either a parsed JSON value or a JSON string (string is parsed with parseJsonStrict first). Failure returns isError with CanonicalizationCode — it does not emit partial bytes. Returns { canonical } or an error. Example: canonicalize_json({ value: { b: 1, a: 2 } }) → {"a":2,"b":1}.
| Name | Type | Req | Description |
|---|---|---|---|
| value | – | yes | JSON value to canonicalize, or a JSON string to parse first. Objects have keys sorted by UTF-16 code units. Numbers must be integers in ±(2^53−1). Do not pass undefined, functions, or cyclic structur… |
| Name | Type | Req | Description |
|---|---|---|---|
| canonical | string | yes | RFC 8785 canonical JSON text (UTF-8-ready string). Hash or sign these bytes, not JSON.stringify output. |
No examples provided.
check_egress_url Check a URL against a WARDEN egress allowlist ~312
Ask EgressGuard whether a URL's hostname is on an operator allowlist. A tool reaching a host you never listed is the classic phone-home tell. Empty allowlist blocks everything (fail-closed), not everything-allowed. When to use: a tool is about to fetch/post and you want the same check a host should wrap around that request. Hostnames match case-insensitively; "*.example.com" matches subdomains, not the apex. When NOT to use: vetting tool definitions (vet_mcp_server / static_scan_tools); canonicalizing JSON (canonicalize_json). This does not fetch the URL and does not inspect tool text. Behaviour: local URL parse + hostname match. Unparseable URLs are refused. No DNS, no HTTP. Idempotent. Returns { allowed, host?, reason? }. Example: check_egress_url({ url: "https://api.github.com/repos", allowlist: ["api.github.com", "*.internal.example.com"] }).
| Name | Type | Req | Description |
|---|---|---|---|
| allowlist | array | yes | Permitted hostnames. Exact match, or leading "*." for subdomains ("*.example.com" matches api.example.com, not example.com). Empty array blocks every host. Entries are trimmed and compared case-insen… |
| url | string | yes | Absolute URL the tool wants to open (https://host/path). Only the hostname is compared; path, query, and credentials are not allowlisted separately. Must be parseable by the WHATWG URL parser. |
| Name | Type | Req | Description |
|---|---|---|---|
| allowed | boolean | yes | true only when the hostname matches an allowlist entry. |
| host | string | – | Parsed hostname when the URL was valid. |
| reason | string | – | Why the request is blocked; omitted when allowed is true. |
No examples provided.
classify_sensitive_tools Classify MCP tools as sensitive vs safe by glob policy ~299
Split advertised tool names into sensitive vs safe using the operator's case-insensitive * globs (the same policy.sensitiveToolPatterns a host would use). Sensitive tools stay advertised; they require per-call approval — this tool does not run them. When to use: show the user which names will need confirmation before they approve a server, or to preview a glob set. This is policy over identifiers, not an injection scan. When NOT to use: scanning descriptions for poisoning (static_scan_tools or vet_mcp_server); checking whether a URL is allowed out (check_egress_url). Behaviour: local glob match, no network. An empty patterns array marks every tool safe. Patterns match the whole name; "*delete*" hits create_delete_repo. Does not call Warden.vet and does not persist anything. Returns { sensitive, safe }. Example: classify_sensitive_tools({ tools: [{ name: "delete_repo", description: "Delete a repository.", inputSchema: { type: "object" } }], patterns: ["*delete*"] }).
| Name | Type | Req | Description |
|---|---|---|---|
| patterns | array | yes | Operator globs, case-insensitive, matched against the whole tool name. "*" is the only wildcard. Empty array → every tool is safe. Same semantics as WardenPolicy.sensitiveToolPatterns, not threat-fee… |
| tools | array | yes | tools/list items whose names will be classified. Descriptions and schemas are ignored; only name is matched. |
| Name | Type | Req | Description |
|---|---|---|---|
| safe | array | yes | Names matching no pattern. |
| sensitive | array | yes | Names matching at least one pattern. Still advertised; require per-call approval. |
No examples provided.
list_scan_rules List the published WARDEN static-scan rule table ~261
Return the in-force static-scan ruleset: version, digest, and every rule's code, severity, tier (block vs advise), surfaces (name / description / inputSchema / title / outputSchema / annotations / metadata), optional regex source, and named guards. A recorded verdict is only reproducible together with this identity. When to use: explain a finding code, confirm the current ruleset version and digest, or re-run a scan with the same table. include_source=true adds the regex source and flags for an independent re-implementation. When NOT to use: evaluating a live tools/list (static_scan_tools or vet_mcp_server — those apply the table). This tool does not scan anything. Behaviour: local snapshot of the compiled rule table, no network, no mutation. Digest is sha256 over the RFC 8785 form of {version, fold, rules} (each rule carries its `raw` flag). Returns the ruleset object. Example: list_scan_rules({ include_source: false }).
| Name | Type | Req | Description |
|---|---|---|---|
| include_source | boolean | – | When true, each rule includes source (regex body) and flags so a third party can re-run the exact pattern. Default false — identity, tier, surfaces, and guards only, smaller payload. |
| Name | Type | Req | Description |
|---|---|---|---|
| digest | string | yes | sha256-<base64> of the canonical rule table (preimage {version, fold, rules}). |
| fold | string | yes | Identity of the text normalisation applied before a non-raw rule is matched. |
| rules | array | yes | – |
| version | string | yes | Monotonic ruleset version. |
No examples provided.
revoke_mcp_server Delete the stored approval for an MCP server ~325
Delete the stored approval for one server id. Afterwards vet_mcp_server treats the server as never seen: its tools are unpinned again until someone approves them anew. When to use: an operator no longer trusts a server, or wants its next approval to start from a clean review. Take previousRevision from status_mcp_server first; the call is refused if the approval changed after that. When NOT to use: to approve a changed server (approve_mcp_server replaces the old approval directly); to block a server for everyone (a revoked server is unpinned, not blocked — use a threat feed or policy for that); to inspect state (status_mcp_server). Behaviour: deletes one file in the local state directory; cannot be undone except by approving again. Refused unless the operator started this process with WARDEN_ALLOW_PIN_CHANGES=1. Needs no tools payload. No network. Returns { revoked: true, serverId }. Example: revoke_mcp_server({ server: { id: "demo@0", name: "demo", transport: "stdio", command: "npx" }, previous_pin_revision: "<previousRevision>" }).
| Name | Type | Req | Description |
|---|---|---|---|
| previous_pin_revision | string|null | yes | The previousRevision value status_mcp_server returned when you reviewed this server (null when it reported no stored approval). The write is refused if the stored approval changed since then, so two… |
| server | object | yes | Server whose approval to delete. Only id is used to find it; the other fields must still be valid. |
| Name | Type | Req | Description |
|---|---|---|---|
| revoked | boolean | yes | Always true; any refusal is returned as an error instead. |
| serverId | string | yes | The server id whose approval was deleted. |
No examples provided.
static_scan_tools Static-scan MCP tool definitions for injection and exfil ~268
Run only the static-scan gate (signatures with context guards, text folded first) over every advertised tool field: name, description, input schema, title, output schema, annotations and extension metadata. Returns findings, a 0..1 gate score, and the published ruleset digest. Use list_scan_rules for the current rule table and identity. When to use: you have a tools/list dump and want injection / credential / hidden-Unicode hits without origin, pinning, or the threat feed. Cheaper and narrower than vet_mcp_server. When NOT to use: you need the full host decision (vet_mcp_server); you want operator glob classification (classify_sensitive_tools); you want the published rule table itself (list_scan_rules). Behaviour: local regex+guard evaluation, no network, no mutation. Advisory-tier hits are reported with advisory=true and do not reduce the score. Does not launch servers or send tool output to a model. Returns structured JSON matching outputSchema. Example: static_scan_tools({ tools: [{ name: "add", description: "Add two integers.", inputSchema: { type: "object" } }] }).
| Name | Type | Req | Description |
|---|---|---|---|
| tools | array | yes | tools/list items to scan (1..256). Same shape as vet_mcp_server.tools. |
| Name | Type | Req | Description |
|---|---|---|---|
| findings | array | yes | Hits from the 36-rule table, including advisory-only codes. |
| ruleset | object | yes | – |
| score | number | yes | static-scan gate contribution: 1 minus the penalty for the worst non-advisory severity. Advisory hits do not change this number. |
No examples provided.
status_mcp_server Show the stored approval for one MCP server ~449
Read the approval WARDEN has stored for one server id and compare it with the tools/list payload and launch identity you pass in. Returns the stored approval (or null), its revision, the hashes of what you passed, whether they differ, what changed field by field (words added and removed in descriptions, schema values before and after, changes made only of numbers marked), and whether this process may change approvals at all. When to use: before an operator decides to approve or revoke a server, to see what changed since the last approval; show the operator reviewText. It is the only source of the values approve_mcp_server and revoke_mcp_server ask for (currentToolsHash, currentIdentityHash, previousRevision). When NOT to use: deciding whether a server is safe to expose (vet_mcp_server runs every gate; this tool runs none). It does not scan descriptions and never blocks. Behaviour: read-only. Reads one file from the local state directory (WARDEN_STATE_DIR, default ~/.local/state/warden/pins); writes nothing, no network, never starts the target server. Works whether or not WARDEN_ALLOW_PIN_CHANGES is set. Returns structured JSON matching outputSchema. Example: status_mcp_server({ server: { id: "demo@0", name: "demo", transport: "stdio", command: "npx" }, tools: [{ name: "add", description: "Add two integers.", inputSchema: { type: "object" } }] }).
| Name | Type | Req | Description |
|---|---|---|---|
| server | object | yes | Identity of the MCP server being vetted — the host's McpServerRef, not a live connection. WARDEN never launches this command or fetches this URL. |
| server_info | object | – | Optional: the serverInfo object from the server's initialize result, unmodified ({ name, version }). Shown next to the review as the version the server reports, and stored with an approval; it is the… |
| tools | array | yes | The server's current tools/list payload, unmodified. Its hash is compared with the stored approval and returned as currentToolsHash. |
| Name | Type | Req | Description |
|---|---|---|---|
| changed | boolean | yes | true when an approval is stored and the tools or the launch identity differ from it. |
| changes | – | – | What changed since the stored approval, field by field; null when nothing is stored. |
| currentIdentityHash | string | yes | Hash of the launch identity (transport, command, args, url, name); pass it as reviewed_identity_hash. |
| currentTools | array | yes | The tool definitions that were hashed, echoed for the operator's review. |
| currentToolsHash | string | yes | Hash of the tools you passed; pass it as reviewed_tools_hash to approve exactly these definitions. |
| mutationsEnabled | boolean | yes | false means approve_mcp_server and revoke_mcp_server will refuse in this process. |
| origin | object | – | Where a change came from: the versions the server reported and whether the launch command pins one. |
| previous | – | yes | The stored approval, or null when this server was never approved or was revoked. |
| previousRevision | string|null | yes | sha256 of the stored approval; pass it as previous_pin_revision. null when nothing is stored. |
| reviewText | string | – | The same changes as plain lines for a person: where they came from (reported version, launch command), [-removed-] and {+added+} inside text, before → after for values, and which tools gain text abou… |
| serverId | string | yes | The server id that was looked up. |
No examples provided.
vet_mcp_server Vet an MCP server through the full WARDEN gate chain ~461
Run WARDEN's ordered gate chain (static-scan → threat-feed → origin → pinning) over a server identity plus its advertised tools/list payload and return a recordable verdict (allow/block, 0..1 product score, findings, allowedTools/blockedTools, ruleset digest). When to use: you have a complete server record and want the same decision a host should make before any of those tool definitions reach the model. Prefer this over calling the four gates yourself. When NOT to use: inspecting descriptions only (call static_scan_tools — no origin/pinning); splitting tools by operator glob (classify_sensitive_tools); checking one outbound URL (check_egress_url); producing RFC 8785 bytes (canonicalize_json). Behaviour: local, deterministic, no network. This stdio process uses the built-in 11-record threat floor (it does not fetch a signed feed) and a durable local pin store. First contact is TOOL_DEF_UNPINNED/advisory until explicitly approved. Origin defaults to allowUnknownServers=true so catalog-discovered servers are not fail-closed. Override policy when you need the host's real knobs. Does not connect to, start, or approve the target server. Returns structured JSON matching outputSchema. Example: vet_mcp_server({ server: { id: "demo@0", name: "demo", transport: "stdio", command: "npx" }, tools: [{ name: "add", description: "Add two integers.", inputSchema: { type: "object" } }] }).
| Name | Type | Req | Description |
|---|---|---|---|
| policy | object | – | Optional WardenPolicy overlay. Omitted keys keep the stdio defaults: blockAtSeverity=high, empty sensitiveToolPatterns, allowUnknownServers=true, pinToolDefs=true. Use classify_sensitive_tools when y… |
| server | object | yes | Identity of the MCP server being vetted — the host's McpServerRef, not a live connection. WARDEN never launches this command or fetches this URL. |
| tools | array | yes | Exact tools/list payload (1..256 tools). Each item is name + description + inputSchema from the server. Do not filter before vetting — blockedTools is the partition. |
| Name | Type | Req | Description |
|---|---|---|---|
| allow | boolean | yes | false when a gate was fatal or a non-advisory finding reached blockAtSeverity. |
| allowedTools | array | yes | Tool names individually permitted; the host MUST also require allow=true before exposure. |
| blockAtSeverity | string | yes | Policy threshold this verdict was decided under: non-advisory findings at or above it block. Store it with the scan beside rulesets. |
| blockedTools | array | yes | Tool names quarantined; the rest of the server may still be usable. |
| decidedBy | string | – | Gate that produced the blocking decision, present only when allow is false. |
| findings | array | yes | Accumulated findings across all gates, including advisory. |
| rulesets | object | yes | Rule-table identity in force for this verdict. Store this with the scan. |
| score | number | yes | Product of per-gate scores in [0, 1]. One bad gate drags the whole server down; it is not an average. |
No examples provided.
How do I install the WARDEN by AIMarket — MCP tool firewall server?
WARDEN by AIMarket — MCP tool firewall runs locally as an npm package, launched with npx -y @aimarket/warden. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @aimarket/warden
claude mcp add alexar76-warden -- npx -y @aimarket/warden
What is the WARDEN by AIMarket — MCP tool firewall server?
WARDEN by AIMarket — MCP tool firewall is listed in the public MCP registry as io.github.alexar76/warden. MCP security firewall: stdio wrap proxy or inspection tools; zero runtime dependencies. This page covers its npm package (@aimarket/warden).
Is the WARDEN by AIMarket — MCP tool firewall server safe to use?
WARDEN by AIMarket — MCP tool firewall scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 WARDEN by AIMarket — MCP tool firewall server expose?
WARDEN by AIMarket — MCP tool firewall exposes 9 tools: vet_mcp_server, static_scan_tools, classify_sensitive_tools, check_egress_url, canonicalize_json, and 4 more. Their descriptions and schemas cost roughly 3,153 tokens of context every time the server is loaded.
Is the WARDEN by AIMarket — MCP tool firewall server still maintained?
WARDEN by AIMarket — MCP tool firewall is still listed as active in the MCP registry. We last reached this channel on 21 November 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 WARDEN by AIMarket — MCP tool firewall server under?
WARDEN by AIMarket — MCP tool firewall declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the WARDEN by AIMarket — MCP tool firewall server?
VerifyMCP ran 15 checks on WARDEN by AIMarket — MCP tool firewall, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about WARDEN by AIMarket — MCP tool firewall: Malware scan. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.