com.scopeblind/protect-mcp
NPM · PROTECT-MCP
Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
Available components
Last scanned (20 hours ago)
Scores higher than 92% 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 Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 97 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to ScopeBlind/scopeblind-gateway). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 26 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability74
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 828 tokens (~207/item across 4 items; 4 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (16)
- Malware scan
- 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
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.
- 20 Nov 26 +1
- Stability: 0.97 → pass security
- 19 Nov 26 −1
- Stability: pass → 0.97 functional
- 17 Nov 26 0
- Package version: 0.31.1 → 0.32.4 functional
- 13 Nov 26 +1
- Stability: 0.97 → pass security
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +1
- Package version: 0.31.1 → 0.32.4 functional
- 7 Nov 26 −3
- Stability: pass → 0.80 functional
- 1 Nov 26 +1
- Stability: 0.97 → pass security
- Security disclosure: unverified → pass ▲ functional
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/protect-mcp@0.32.4
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | ScopeBlind/scopeblind-gateway |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/ScopeBlind/scopeblind-gateway/.github/workflows/publish.yml@refs/heads/main |
| Rekor log index | 3471831461 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:f686011e64f9acbc5f4db9abd22816b185c279595cb740d932cbc0721f51d985b78e313efdf40aead7ab2f5b72e2192c362e4343bf0a8cc5e91e385a7 |
Background: How many MCP packages publish verified provenance →
Dependencies 97 packages
| Packages resolved | 97 |
|---|---|
| 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 →
evaluate_action ~251
Decide whether a proposed agent tool call is allowed by a Cedar policy, fail-closed. Evaluates the call against the policy the same way the protect-mcp gate does at runtime, and on any policy error the decision is DENY (never a silent allow). Inputs: tool (the tool name, e.g. "Bash" or "send_email"), input (the tool's arguments object; the policy sees it at context.input.*), and policy (inline Cedar source text). Returns JSON { allowed: boolean, decision: "allow" | "deny", reason: string, policy_digest: string (sha256 prefix of the policy) }. A missing or unparseable policy denies. Use this before an agent acts; pair with sign_decision to make the decision auditable.
| Name | Type | Req | Description |
|---|---|---|---|
| input | object | – | The tool's arguments. Reachable in the policy at context.input.* (e.g. context.input.command). |
| policy | string | yes | Inline Cedar policy source. Use MCP::Tool::call as the action and Tool::"<name>" as the resource. |
| tool | string | yes | The tool name being evaluated, e.g. "Bash", "Write", "send_email". |
No output schema declared.
No examples provided.
self_test ~110
Prove the gate works, end to end, with no inputs. Runs a known-forbidden action (rm -rf) against a sample deny policy and asserts it is DENIED, then signs a decision and verifies the receipt round-trips. Returns JSON { ok: boolean, gate_denies_forbidden: boolean, sign_verify_roundtrip: boolean, details: object }. This is the 'a gate that cannot prove it denies does not start' check, exposed as a callable tool. Contacts no network.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
sign_decision ~293
Turn a gate decision into an Ed25519 signed receipt (Veritas Acta format, JCS-canonical). A denial signs a gateway_restraint artifact; an allow signs a decision_receipt. This is what makes 'what the agent was blocked from doing' provable after the fact. Inputs: tool (required), decision ("allow" | "deny", required), reason_code (optional), policy_digest (optional), and private_key_hex (optional 64-hex Ed25519 secret; if omitted, an ephemeral keypair is generated and its public key is returned so the receipt still verifies). Returns JSON { receipt: object (the signed artifact), artifact_type: "decision_receipt" | "gateway_restraint", public_key: string (hex, pass this to verify_receipt or pin it), ephemeral: boolean }. Writes nothing to disk and contacts no network.
| Name | Type | Req | Description |
|---|---|---|---|
| decision | string | yes | The gate decision to receipt. |
| policy_digest | string | – | Optional digest of the policy that produced the decision (e.g. from evaluate_action). |
| private_key_hex | string | – | Optional 64-character hex Ed25519 secret key. If omitted, an ephemeral key is generated and its public key is returned. |
| reason_code | string | – | Optional machine reason, e.g. "restricted_list" or "post_execution_receipt". |
| tool | string | yes | The tool the decision is about. |
No output schema declared.
No examples provided.
verify_receipt ~174
Verify a signed receipt offline against a public key. No network, no accounts: the Ed25519 signature is checked over the canonical bytes. Inputs: receipt (the signed artifact object, required) and public_key_hex (optional; falls back to a public_key embedded in the receipt payload). Returns JSON { valid: boolean, error: string | null (e.g. "invalid_signature", "no_public_key"), type: string, kid: string | null, issuer: string | null }. For authenticity you should verify against a key you pinned out of band, not only the one carried inside the receipt.
| Name | Type | Req | Description |
|---|---|---|---|
| public_key_hex | string | – | Optional Ed25519 public key hex to verify against. Defaults to a key embedded in the receipt payload. |
| receipt | object | yes | The signed receipt/artifact to verify. |
No output schema declared.
No examples provided.
How do I install the com.scopeblind/protect-mcp server?
com.scopeblind/protect-mcp runs locally as an npm package, launched with npx -y protect-mcp 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 · protect-mcp
claude mcp add com-scopeblind-protect-mcp -- npx -y protect-mcp mcp
What is the com.scopeblind/protect-mcp server?
com.scopeblind/protect-mcp is listed in the public MCP registry as com.scopeblind/protect-mcp. Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error. This page covers its npm package (protect-mcp).
Is the com.scopeblind/protect-mcp server safe to use?
com.scopeblind/protect-mcp scores 92 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. Its build provenance is signed and verified. 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.scopeblind/protect-mcp server expose?
com.scopeblind/protect-mcp exposes 4 tools: evaluate_action, sign_decision, verify_receipt, self_test. Their descriptions and schemas cost roughly 828 tokens of context every time the server is loaded.
Is the com.scopeblind/protect-mcp server still maintained?
com.scopeblind/protect-mcp 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 com.scopeblind/protect-mcp server under?
com.scopeblind/protect-mcp 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 com.scopeblind/protect-mcp server?
VerifyMCP ran 16 checks on com.scopeblind/protect-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.