# io.github.robinlidberg-dot/cap-shield (pypi · cap-shield)

Context selection and compression for AI agents - recall measured, not claimed.

- Trust score: 78/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- pypi · `cap-shield`: 78/100 (this document), [markdown](https://verifymcp.io/servers/robinlidberg-dot-cap-shield/cap-shield.md), [page](https://verifymcp.io/servers/robinlidberg-dot-cap-shield/cap-shield)

## Channel facts

- Registry: `pypi`
- Package: `cap-shield`
- Version: `0.4.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 0 of 9 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 483 tokens (~96/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 87/100
  - Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 64% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the io.github.robinlidberg-dot/cap-shield MCP server?

io.github.robinlidberg-dot/cap-shield runs locally as a PyPI package, launched with uvx cap-shield. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add robinlidberg-dot-cap-shield -- uvx cap-shield
```

### Cursor

```json
{
  "mcpServers": {
    "robinlidberg-dot-cap-shield": {
      "command": "uvx",
      "args": [
        "cap-shield"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "robinlidberg-dot-cap-shield": {
      "command": "uvx",
      "args": [
        "cap-shield"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add robinlidberg-dot-cap-shield -- uvx cap-shield
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "robinlidberg-dot-cap-shield": {
      "type": "local",
      "command": [
        "uvx",
        "cap-shield"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add robinlidberg-dot-cap-shield --command uvx --arg cap-shield
```

### Hermes

```yaml
mcp_servers:
  robinlidberg-dot-cap-shield:
    command: "uvx"
    args: ["cap-shield"]
```

### Netclaw

```json
{
  "McpServers": {
    "robinlidberg-dot-cap-shield": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "cap-shield"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add robinlidberg-dot-cap-shield -t stdio -c uvx -a cap-shield
```

### Other

```json
{
  "mcpServers": {
    "robinlidberg-dot-cap-shield": {
      "command": "uvx",
      "args": [
        "cap-shield"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `measure_traffic` (~143 tokens)

Measure how much of your own agent traffic could be saved. NO ACCOUNT OR KEY NEEDED — use this first. Returns byte savings over the wire and, if a query is given, token savings from selective context retrieval. Nothing is stored: the text is compressed in memory and discarded. Rate limited to 20 calls per hour per IP.

Input parameters:

- `dict_id` (string): Which trained dictionary to measure against. Call list_packages to see the options and their measured figures.
- `query` (string): Optional. What your agent would search its memory for. Given this, token savings are measured too.
- `texts` (array, required): Your actual messages. 200 max.

### `list_packages` (~56 tokens)

List the available dictionaries with their MEASURED compression, including the ones that perform badly. Each entry says whether it works one message at a time or only batched, and how many messages came out LARGER. No key needed.

### `remember` (~89 tokens)

Store a memory entry for later retrieval. REQUIRES A KEY. This does not call any language model — it stores text in an isolated per-tenant archive. Use assemble_context to get relevant entries back.

Input parameters:

- `item_id` (string): Optional. Same id overwrites the entry. Omit for a generated one.
- `namespace` (string, required): Groups related memories.
- `text` (string, required)

### `assemble_context` (~121 tokens)

Retrieve the memory entries that answer a question, within a token budget. REQUIRES A KEY. Send the returned 'context' to your language model INSTEAD of the whole history. This does not call a model itself — it selects what to send. The budget is a ceiling, not a target: selection stops where relevance runs out, often well below it. The response says how many entries were left behind and why.

Input parameters:

- `namespace` (string, required)
- `query` (string, required): What you need context about.
- `token_budget` (integer)

### `get_account` (~74 tokens)

Get an account and an API key. Requires an email address. The key is returned ONCE and cannot be shown again — store it immediately. Beta quotas are low by design; they are hard stops, never overage billing.

Input parameters:

- `email` (string, required)
- `traffic` (string): Optional. What your agent sends.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/robinlidberg-dot-cap-shield/cap-shield#diagnostics

## Score history

- 2026-09-21: 78
- 2026-09-20: 78
- 2026-09-19: 77
- 2026-09-18: 77
- 2026-09-17: 76
- 2026-09-16: 76
- 2026-09-15: 76
- 2026-09-14: 75
- 2026-09-13: 75
- 2026-09-12: 74
- 2026-09-11: 74
- 2026-09-10: 73
- 2026-09-09: 73
- 2026-09-08: 72
- 2026-09-07: 72
- 2026-09-06: 71
- 2026-09-05: 71
- 2026-09-04: 70
- 2026-09-03: 70
- 2026-09-02: 66
- 2026-09-01: 66
- 2026-08-31: 66
- 2026-08-30: 66
- 2026-08-29: 66
- 2026-08-28: 66
- 2026-08-27: 66
- 2026-08-26: 51

## Common questions

### What is the io.github.robinlidberg-dot/cap-shield MCP server?

io.github.robinlidberg-dot/cap-shield is an MCP server listed in the public MCP registry as io.github.robinlidberg-dot/cap-shield. Context selection and compression for AI agents - recall measured, not claimed. This page covers its PyPI package (cap-shield).

### Is the io.github.robinlidberg-dot/cap-shield MCP server safe to use?

io.github.robinlidberg-dot/cap-shield scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 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 io.github.robinlidberg-dot/cap-shield MCP server expose?

io.github.robinlidberg-dot/cap-shield exposes 5 tools: measure_traffic, list_packages, remember, assemble_context, get_account. Their descriptions and schemas cost roughly 483 tokens of context every time the server is loaded.

### Is the io.github.robinlidberg-dot/cap-shield MCP server still maintained?

io.github.robinlidberg-dot/cap-shield is still listed as active in the MCP registry. We last reached this channel on 21 September 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 io.github.robinlidberg-dot/cap-shield MCP server under?

io.github.robinlidberg-dot/cap-shield declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/cap-shield/
- Socket report: https://socket.dev/pypi/package/cap-shield
- Repository: https://github.com/robinlidberg-dot/cap-shield-mcp
- Website: https://cap-shield-robin.fly.dev/
- Changelog RSS feed: https://verifymcp.io/servers/robinlidberg-dot-cap-shield/cap-shield.xml
- Changelog JSON feed: https://verifymcp.io/servers/robinlidberg-dot-cap-shield/cap-shield.json
- HTML version of this page: https://verifymcp.io/servers/robinlidberg-dot-cap-shield/cap-shield