# ctxcap (npm · ctxcap-mcp)

Offline context-budget MCP server for AI coding agents.

- Trust score: 65/100 (medium)
- Change this week: +27
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `ctxcap-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/naeha-s-ctxcap/ctxcap-mcp.md), [page](https://verifymcp.io/servers/naeha-s-ctxcap/ctxcap-mcp)

## Channel facts

- Registry: `npm`
- Package: `ctxcap-mcp`
- Version: `0.1.10`
- 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 2026-11-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 10 of 20 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 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 451 tokens (~112/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 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 ctxcap MCP server?

ctxcap runs locally as an npm package, launched with npx -y ctxcap-mcp. 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 naeha-s-ctxcap -- npx -y ctxcap-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "naeha-s-ctxcap": {
      "command": "npx",
      "args": [
        "-y",
        "ctxcap-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "naeha-s-ctxcap": {
      "command": "npx",
      "args": [
        "-y",
        "ctxcap-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add naeha-s-ctxcap -- npx -y ctxcap-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "naeha-s-ctxcap": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "ctxcap-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add naeha-s-ctxcap --command npx --arg -y --arg ctxcap-mcp
```

### Hermes

```yaml
mcp_servers:
  naeha-s-ctxcap:
    command: "npx"
    args: ["-y", "ctxcap-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "naeha-s-ctxcap": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "ctxcap-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add naeha-s-ctxcap -t stdio -c npx -a -y ctxcap-mcp
```

### Other

```json
{
  "mcpServers": {
    "naeha-s-ctxcap": {
      "command": "npx",
      "args": [
        "-y",
        "ctxcap-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-20 (score 65, +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.

### 2026-11-19 (score 64, 0)

- [security improvement] CVE-2026-112366 no longer affects this package
- [security improvement] Known CVEs: partial → pass

### 2026-11-18 (score 64, +1)

- [security regression] CVE-2026-112366 affects this package
- [security regression] Known CVEs: pass → partial

### 2026-11-17 (score 63, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.79

### 2026-11-16 (score 52, +14)

- [security regression] Known CVEs: pass → unverified
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Tool safety: Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] MCP protocol: unverified → fail
- [functional regression] Dependency health: 0.79 → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.00
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet.
- [functional] Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet.
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Package version: 0.1.4 → 0.1.10
- [functional] Package version: 0.1.4 → 0.1.9

### 2026-11-13 (score 38)

First indexed and scored.

## MCP tools (4)

### `measure_context` (~104 tokens)

Use when CLAUDE.md, AGENTS.md, Cursor rules, or prompts may be too large or consuming too much context. Input: optional suggest, stale, and staleGlob booleans. Returns JSON token totals, per-file counts, baseline deltas, budget status, suggestions, and optional stale-reference findings. Runs offline and only reads the current working directory.

Input parameters:

- `stale` (boolean)
- `staleGlob` (boolean)
- `suggest` (boolean)

### `context_budget_plan` (~180 tokens)

Use before appending more than ~50 lines or when CLAUDE.md, AGENTS.md, Cursor rules, or prompts exceed budget. Input: required integer budget plus optional maxFindings, includeDiff, and apply. Returns a deterministic ranked plan with file line ranges, tokensFreed, confidence, safety actions, preserve spans, and satisfiable/minAchievable stop state. Apply entries in order by startLine/endLine, never rewrite a file, never cut preserve spans except by applying the condensedText of a condense entry exactly as given, stop when satisfiable is false, and call context_budget_verify after edits. The plan is saved under .ctxcap/plans for 24 hours.

Input parameters:

- `apply` (boolean)
- `budget` (integer, required)
- `includeDiff` (boolean)
- `maxFindings` (integer)

### `context_budget_verify` (~79 tokens)

Use after applying a context-budget plan to catch missed edits, manual drift, or preserve-span violations. Input: the planId returned by context_budget_plan. Returns applied and missed finding IDs, violations with file and line ranges, remaining tokens, and satisfied. Do not consider the budget met until satisfied is true.

Input parameters:

- `planId` (string, required)

### `trim_to_budget` (~88 tokens)

Deprecated alias for context_budget_plan for clients using the old name. Input: required integer budget and optional maxFindings. Returns the same ranked, safety-classified plan with apply false; it never edits context files. Follow line ranges, preserve spans, satisfiable stop rules, and verification guidance from context_budget_plan.

Input parameters:

- `budget` (integer, required)
- `maxFindings` (integer)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/naeha-s-ctxcap/ctxcap-mcp#diagnostics

## Score history

- 2026-11-21: 65
- 2026-11-20: 65
- 2026-11-19: 64
- 2026-11-18: 64
- 2026-11-17: 63
- 2026-11-16: 52
- 2026-11-15: 38
- 2026-11-14: 38
- 2026-11-13: 38

## Common questions

### What is the ctxcap MCP server?

ctxcap is an MCP server listed in the public MCP registry as io.github.Naeha-S/ctxcap. Offline context-budget MCP server for AI coding agents. This page covers its npm package (ctxcap-mcp).

### Is the ctxcap MCP server safe to use?

ctxcap scores 65 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. 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 ctxcap MCP server expose?

ctxcap exposes 4 tools: measure_context, context_budget_plan, context_budget_verify, trim_to_budget. Their descriptions and schemas cost roughly 451 tokens of context every time the server is loaded.

### Is the ctxcap MCP server still maintained?

ctxcap 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 ctxcap MCP server under?

ctxcap 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 ctxcap MCP server?

VerifyMCP ran 16 checks on ctxcap, 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.

## Links

- npm package: https://www.npmjs.com/package/ctxcap-mcp
- Socket report: https://socket.dev/npm/package/ctxcap-mcp
- Repository: https://github.com/Naeha-S/ctxcap
- Website: https://naeha-s.github.io/ctxcap/
- Changelog RSS feed: https://verifymcp.io/servers/naeha-s-ctxcap/ctxcap-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/naeha-s-ctxcap/ctxcap-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/naeha-s-ctxcap/ctxcap-mcp.json
- HTML version of this page: https://verifymcp.io/servers/naeha-s-ctxcap/ctxcap-mcp
