Keel
PYPI · KEEL-PENTEST
Control plane MCP that dedups scanner output, rate-limits hosts, and runs non-destructive proofs.
Available components
Last scanned (16 hours ago)
Scores higher than 62% of PyPI 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
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 31 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 (MIT).Pass
- Actively maintained (last published 55 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability51
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 715 tokens (~55/item across 13 items; 13 tools + 0 resources), lean.Pass
- 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 Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_wave" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- 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 current MCP spec version (2026-07-28).Pass
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.
- 17 Oct 26 +3
- Stability: 0.80 → pass security
- 16 Oct 26 −3
- Stability: pass → 0.80 functional
- 15 Oct 26 0
- Stability: 0.97 → pass security
- 14 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- 13 Oct 26 0
- Package version: 0.1.1 → 0.3.0 functional
- 12 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- 4 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Security disclosure: unverified → fail ▼ functional
- 3 Oct 26 +1
- Security disclosure: fail → unverified ▼ 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 18 Oct 2026 · Analysed pypi/keel-pentest@0.3.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 31 packages
| Packages resolved | 31 |
|---|---|
| No linked repository | 1 |
| 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 →
assess_exploitability ~40
Explain candidate impact, missing evidence, controls, and safe proof options.
| Name | Type | Req | Description |
|---|---|---|---|
| card_id | string | yes | – |
| engagement_id | string | yes | – |
No output schema declared.
No examples provided.
begin_engagement ~202
Register exact/wildcard scope and bounded traffic policy. Default mode is self-attested: calling begin_engagement is the authorization. Set KEEL_APPROVAL_FILE for optional strict/team manifests. The legacy operator_confirmed argument is ignored and cannot grant approval.
| Name | Type | Req | Description |
|---|---|---|---|
| allow_safe_proof | boolean | – | – |
| engagement_id | string | yes | – |
| exclude_hosts | – | – | – |
| max_engagement_requests | integer | – | – |
| max_parallel_hosts | integer | – | – |
| max_proof_requests | integer | – | – |
| max_response_bytes | integer | – | – |
| max_wave_attempts | integer | – | – |
| max_wave_requests | integer | – | – |
| max_wave_seconds | integer | – | – |
| nuclei_template_ids | – | – | – |
| operator_confirmed | boolean | – | – |
| requests_per_second | number | – | – |
| scope_hosts | array | yes | – |
| tester_account_a | string | – | – |
| tester_account_b | string | – | – |
No output schema declared.
No examples provided.
cancel_wave ~34
Request cancellation of a queued or running scanner process.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | string | yes | – |
| job_id | string | yes | – |
No output schema declared.
No examples provided.
draft_proof ~43
Describe an allowlisted proof without sending traffic.
| Name | Type | Req | Description |
|---|---|---|---|
| card_id | string | yes | – |
| engagement_id | string | yes | – |
| playbook_id | string | yes | – |
No output schema declared.
No examples provided.
draft_waves ~39
Draft reachability plus one micro-wave per reviewed template; no traffic.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | string | yes | – |
| seed_url | string | yes | – |
No output schema declared.
No examples provided.
engagement_audit ~35
Return recent append-only application audit events for one engagement.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | string | yes | – |
| limit | integer | – | – |
No output schema declared.
No examples provided.
engagement_health ~25
Report registered engagements, cooldowns, and pending waves.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | – | – | – |
No output schema declared.
No examples provided.
execute_proof ~84
Run a proof bound to an operator-approved target, credentials, and canary hash.
| Name | Type | Req | Description |
|---|---|---|---|
| card_id | string | yes | – |
| engagement_id | string | yes | – |
| expected_marker | string | – | – |
| playbook_id | string | yes | – |
| proof_target_ref | string | – | – |
| session_a | string | – | – |
| session_b | string | – | – |
No output schema declared.
No examples provided.
execute_wave ~37
Start one admitted wave in the background and return its persistent job.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | string | yes | – |
| wave_id | string | yes | – |
No output schema declared.
No examples provided.
query_cards ~40
Return hunter-relevant cards. Informational and hardening are hidden by default.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | string | yes | – |
| include_noise | boolean | – | – |
No output schema declared.
No examples provided.
second_look ~36
Start a background micro-wave using only the originating template.
| Name | Type | Req | Description |
|---|---|---|---|
| card_id | string | yes | – |
| engagement_id | string | yes | – |
No output schema declared.
No examples provided.
state_impact ~60
Record hunter impact_class and preconditions on a card.
| Name | Type | Req | Description |
|---|---|---|---|
| card_id | string | yes | – |
| engagement_id | string | yes | – |
| hunter_why | string | yes | – |
| impact | string | yes | – |
| preconditions | string | yes | – |
No output schema declared.
No examples provided.
wave_status ~40
Return one job, or list persistent jobs/waves when job_id is omitted.
| Name | Type | Req | Description |
|---|---|---|---|
| engagement_id | string | yes | – |
| job_id | string | – | – |
No output schema declared.
No examples provided.
How do I install the Keel MCP server?
Keel runs locally as a PyPI package, launched with uvx keel-pentest. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · keel-pentest
claude mcp add lutfizp-keel -- uvx keel-pentest
What is the Keel MCP server?
Keel is an MCP server listed in the public MCP registry as io.github.lutfizp/keel. Control plane MCP that dedups scanner output, rate-limits hosts, and runs non-destructive proofs. This page covers its PyPI package (keel-pentest).
Is the Keel MCP server safe to use?
Keel scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. 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 Keel MCP server expose?
Keel exposes 13 tools: begin_engagement, draft_waves, execute_wave, wave_status, cancel_wave, and 8 more. Their descriptions and schemas cost roughly 715 tokens of context every time the server is loaded.
Is the Keel MCP server still maintained?
Keel is still listed as active in the MCP registry. We last reached this channel on 18 October 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 Keel MCP server under?
Keel declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.