mcp-armor
OCI · GHCR.IO/STUDIOMEYER-IO/MCP-ARMOR
Security sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks.
Available components
Last scanned (8 hours ago)
Scores higher than 46% of OCI 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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.Unverified
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 3 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability73
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 736 tokens (~66/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage75
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 24% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 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
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 39
First indexed and scored.
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 5 Nov 2026 · Analysed oci/ghcr.io/studiomeyer-io/mcp-armor@0.8.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
armor_check_cve ~60
Look up exact product names or documented aliases in source-verified advisories; report affected, not_affected, or unknown version status. This does not prove scanner coverage.
| Name | Type | Req | Description |
|---|---|---|---|
| server_name | string | yes | – |
| server_version | string | – | – |
No output schema declared.
No examples provided.
armor_get_drift_history ~119
v0.5 Layer 7 — Inspect the tools-list schema-drift baselines persisted by `mcp-armor wrap`. Read-only. Optional `program` arg narrows the report to one upstream; omit it to list every pinned baseline. Closes the Rug-Pull / Silent-Redefinition threat class (Invariant Labs, CyberArk Full-Schema Poisoning).
| Name | Type | Req | Description |
|---|---|---|---|
| program | string | – | When set, return the full per-tool fingerprint detail for one program. When omitted, return a summary list of every pinned baseline. |
No output schema declared.
No examples provided.
armor_get_keystore ~63
v0.2 — List pinned TOFU maintainer public keys (server_name + fingerprint + pinned_at_iso). Read-only inspection of the keystore configured at sidecar startup (no caller-supplied path — operator-only via `--keystore` flag).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
armor_get_policy ~27
Return the active policy: file path, rules, fail mode, scan flags, version.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
armor_list_blocked ~37
Read recent blocked tool calls from the in-memory ring buffer.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| since_iso | string | – | – |
No output schema declared.
No examples provided.
armor_rekor_lookup ~78
v0.2 — Query the Sigstore Rekor transparency log for inclusion of a manifest's artifact hash. Requires --features sigstore-bridge at build time. Network call.
| Name | Type | Req | Description |
|---|---|---|---|
| rekor_url | string | – | Override Rekor endpoint; defaults to https://rekor.sigstore.dev |
| tools_list_response | object | yes | – |
No output schema declared.
No examples provided.
armor_scan_payload ~33
Scan an arbitrary payload for prompt-injection patterns.
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | yes | – |
| payload | string | yes | – |
No output schema declared.
No examples provided.
armor_scan_tools_list ~139
v0.8 Layer 8 — Scan a captured tools/list response for tool-description / full-schema poisoning (model-directed instructions hidden in tool descriptions, parameter schemas, enum values or defaults). Read-only; never spawns the upstream. Pass `tools_list` as the response object or a raw JSON string. Closes the first-sight Tool Poisoning (Invariant Labs) / Full-Schema Poisoning (CyberArk) / OWASP MCP03 class that Layer 7 drift (which only catches later changes) leaves open on the initial baseline.
| Name | Type | Req | Description |
|---|---|---|---|
| tools_list | – | yes | The tools/list response, as a JSON object or a JSON string. |
No output schema declared.
No examples provided.
armor_simulate_attack ~74
Run an internal ARMOR-SIM pattern fixture through the scanner. Not a CVE exploit or product-remediation test. Legacy cve_id input is a migration alias only.
| Name | Type | Req | Description |
|---|---|---|---|
| cve_id | string | – | Legacy simulation alias only; does not assert a CVE relationship. |
| simulation_id | string | – | – |
No output schema declared.
No examples provided.
armor_verify_bundle ~44
v0.2 — Parse a cosign sigstore.json bundle and structurally verify the Rekor SignedEntryTimestamp shape. Offline.
| Name | Type | Req | Description |
|---|---|---|---|
| bundle_json | string | yes | – |
No output schema declared.
No examples provided.
armor_verify_manifest ~62
Verify Ed25519 signature over canonical-JSON form of a tools/list response.
| Name | Type | Req | Description |
|---|---|---|---|
| public_key_b64 | string | yes | – |
| signature_b64 | string | yes | – |
| signed_at_iso | string | – | – |
| tools_list_response | object | yes | – |
No output schema declared.
No examples provided.
How do I install the mcp-armor server?
mcp-armor runs locally as a container image, launched with docker run --rm -i ghcr.io/studiomeyer-io/mcp-armor:0.8.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/studiomeyer-io/mcp-armor
claude mcp add io-studiomeyer-armor -- docker run --rm -i ghcr.io/studiomeyer-io/mcp-armor:0.8.2
What is the mcp-armor server?
mcp-armor is listed in the public MCP registry as io.studiomeyer/armor. Security sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks. This page covers its container image (ghcr.io/studiomeyer-io/mcp-armor).
Is the mcp-armor server safe to use?
mcp-armor scores 41 out of 100 on VerifyMCP. 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 mcp-armor server expose?
mcp-armor exposes 11 tools: armor_scan_payload, armor_verify_manifest, armor_list_blocked, armor_get_policy, armor_check_cve, and 6 more. Their descriptions and schemas cost roughly 736 tokens of context every time the server is loaded.
Is the mcp-armor server still maintained?
mcp-armor is still listed as active in the MCP registry. We last reached this channel on 5 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 mcp-armor server under?
mcp-armor declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.