Phocinae MCP
PYPI · PHOCINAE-MCP
Local Phocinae decision-engine MCP stdio server: fail-closed approval gate + classify/route/score.
Available components
Last scanned (19 hours ago)
Scores higher than 61% 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
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
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 5 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability76
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1026 tokens (~205/item across 5 items; 4 tools + 1 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 Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
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
- 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 6 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
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.
- 18 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 16 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- 14 Oct 26 +32
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- First check of Tool coverage: 100 functional
- 12 Oct 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 18 Oct 2026 · Analysed pypi/phocinae-mcp@0.2.6
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 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 →
classify 分类 ~193
何时使用：需要把一段状态/上下文归入若干已知标签之一（意图分类、类型识别）时。何时不使用：标签未知或不固定时（改走 route 或让模型自由作答）；需要对同一对象打多重分数时（用 score）。返回 choice=选项下标（0 起）、label、置信度；服务不可用返回明确错误。
| Name | Type | Req | Description |
|---|---|---|---|
| labels | array | yes | 候选标签列表（必填；1–100 个非空字符串，单项上限 2000 字符） |
| server | string | – | 可选：覆盖服务地址（http://host:port，等价于 --server；上限 2048 字符） |
| state | string | yes | 待分类的上下文/状态描述（必填；上限 20000 字符） |
| Name | Type | Req | Description |
|---|---|---|---|
| choice | integer | yes | – |
| confidence | number|null | – | – |
| label | string | yes | – |
| labels | array | yes | – |
| model | string|null | – | – |
| question | string | yes | – |
| server | string | – | – |
| state | string | yes | – |
| usage | object|null | – | – |
No examples provided.
gate 命令审批门 ~245
何时使用：需要判定一条 shell 命令能否执行时——代码代理要跑命令、批处理要校验、人工要复核灰区命令，都用 gate 逐条判定。何时不使用：不要用它判定非 shell 操作（文件读写、HTTP 调用）；不要把多条命令拼成一条字符串绕过判定；宿主已有内置审批机制时不要重复叠加。返回 decision ∈ allow|deny|ask 与 layer/reason；ask 时结果携带人工确认交互（MCP 2026-07-28 elicitation）或明示需人工复核；服务不可用 fail-closed 返回 deny。
| Name | Type | Req | Description |
|---|---|---|---|
| command | string | yes | 待判定的 shell 命令（必填；上限 20000 字符） |
| cwd | string | – | 命令执行工作目录（可选；默认服务器进程当前目录） |
| server | string | – | 可选：覆盖服务地址（http://host:port，等价于 --server；上限 2048 字符） |
| Name | Type | Req | Description |
|---|---|---|---|
| command | string | yes | – |
| confidence | number|null | – | – |
| cwd | string | – | – |
| decision | string | yes | – |
| engine | string | – | – |
| error | string | – | – |
| fail_closed | string | – | – |
| human_action | string | – | – |
| layer | string | yes | – |
| model | string|null | – | – |
| noul | number|null | – | – |
| noul_state | string | – | – |
| reason | string | yes | – |
| score | number|null | – | – |
| server | string | – | – |
| status | string | – | – |
| tool | string | – | – |
No examples provided.
route 工具路由 ~200
何时使用：有确定的候选工具/处理器清单、需要从中挑出最合适的一个来服务请求时。何时不使用：候选清单不固定或用户已直接指定工具时（尊重用户指定，不重复路由）；要评估每个候选的质量而非挑选时（用 score 逐个打分）。返回 choice=下标、tool=选中的工具名；服务不可用返回明确错误。
| Name | Type | Req | Description |
|---|---|---|---|
| server | string | – | 可选：覆盖服务地址（http://host:port，等价于 --server；上限 2048 字符） |
| state | string | yes | 请求/上下文描述（必填；上限 20000 字符） |
| tools | array | yes | 候选工具名列表（必填；1–100 个非空字符串，单项上限 2000 字符） |
| Name | Type | Req | Description |
|---|---|---|---|
| choice | integer | yes | – |
| confidence | number|null | – | – |
| model | string|null | – | – |
| question | string | yes | – |
| server | string | – | – |
| state | string | yes | – |
| tool | string | yes | – |
| tools | array | yes | – |
| usage | object|null | – | – |
No examples provided.
score 打分 ~188
何时使用：需要按 criteria 给 state 打 2–10 分（风险、质量、适配度等）时。何时不使用：需要分类（用 classify）、多选一（用 route 或 gate）、或分数语义与 2–10 量纲不符时。返回 score ∈ [2, 10] 与 range；服务不可用或应答越界返回明确错误。
| Name | Type | Req | Description |
|---|---|---|---|
| criteria | array | yes | 打分标准列表（必填；1–100 个非空字符串，单项上限 2000 字符） |
| server | string | – | 可选：覆盖服务地址（http://host:port，等价于 --server；上限 2048 字符） |
| state | string | yes | 待打分对象的状态描述（必填；上限 20000 字符） |
| Name | Type | Req | Description |
|---|---|---|---|
| confidence | number|null | – | – |
| criteria | array | yes | – |
| model | string|null | – | – |
| question | string | yes | – |
| range | array | yes | – |
| score | number | yes | – |
| server | string | – | – |
| state | string | yes | – |
| usage | object|null | – | – |
No examples provided.
How do I install the Phocinae MCP server?
Phocinae MCP runs locally as a PyPI package, launched with uvx phocinae-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · phocinae-mcp
claude mcp add phocinae-phocinae-mcp -- uvx phocinae-mcp
What is the Phocinae MCP server?
Phocinae MCP is listed in the public MCP registry as io.github.Phocinae/phocinae-mcp. Local Phocinae decision-engine MCP stdio server: fail-closed approval gate + classify/route/score. This page covers its PyPI package (phocinae-mcp).
Is the Phocinae MCP server safe to use?
Phocinae MCP scores 56 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 Phocinae MCP server expose?
Phocinae MCP exposes 4 tools: gate, classify, route, score. Their descriptions and schemas cost roughly 826 tokens of context every time the server is loaded.
Is the Phocinae MCP server still maintained?
Phocinae MCP 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 Phocinae MCP server under?
Phocinae MCP 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.