# io.github.capsolver-ai/capsolver-mcp (pypi · capsolver-mcp)

MCP Server for CapSolver - captcha-solving capabilities for AI agents

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `capsolver-mcp`: 67/100 (this document), [markdown](https://verifymcp.io/servers/capsolver-ai-capsolver-mcp/capsolver-mcp.md), [page](https://verifymcp.io/servers/capsolver-ai-capsolver-mcp/capsolver-mcp)

## Channel facts

- Registry: `pypi`
- Package: `capsolver-mcp`
- Version: `0.1.3`
- 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 2026-09-20.

- **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 30 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 878 tokens (~175/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **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**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.capsolver-ai/capsolver-mcp server?

io.github.capsolver-ai/capsolver-mcp runs locally as a PyPI package, launched with uvx capsolver-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 capsolver-ai-capsolver-mcp -- uvx capsolver-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "capsolver-ai-capsolver-mcp": {
      "command": "uvx",
      "args": [
        "capsolver-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "capsolver-ai-capsolver-mcp": {
      "command": "uvx",
      "args": [
        "capsolver-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add capsolver-ai-capsolver-mcp -- uvx capsolver-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add capsolver-ai-capsolver-mcp --command uvx --arg capsolver-mcp
```

### Hermes

```yaml
mcp_servers:
  capsolver-ai-capsolver-mcp:
    command: "uvx"
    args: ["capsolver-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "capsolver-ai-capsolver-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "capsolver-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add capsolver-ai-capsolver-mcp -t stdio -c uvx -a capsolver-mcp
```

### Other

```json
{
  "mcpServers": {
    "capsolver-ai-capsolver-mcp": {
      "command": "uvx",
      "args": [
        "capsolver-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.

### 2026-09-20 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 66, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.1.2 → 0.1.3

### 2026-09-17 (score 65)

First indexed and scored.

## MCP tools (5)

### `solve_captcha` (~436 tokens)

Solve a captcha in token mode — no browser required.

CapSolver will create a task on its server, solve the captcha challenge,
and return the solution token. Use this when you only need the token to
submit to a target website (e.g. via form POST or API call).

Args:
    captcha_type: One of "reCaptchaV2", "reCaptchaV3", "cloudflare".
    website_url: The full URL of the page where the captcha appears.
    website_key: The site key / public key / data-sitekey of the captcha widget.
    version: reCAPTCHA version hint ("v2" or "v3"). Usually auto-detected.
    page_action: reCAPTCHA v3 action name (e.g. "login", "submit").
    min_score: reCAPTCHA v3 minimum score threshold (0.0–1.0).
    invisible: Whether the reCAPTCHA widget uses invisible mode.
    enterprise: Whether to use the Enterprise API variant.
    s_token: Enterprise s_token for stoken-based verification.
    cdata: Cloudflare Turnstile custom data parameter.
    proxy: Proxy in "user:pass@host:port" or "host:port" format.
    user_agent: Custom User-Agent string to use during solving.
    timeout: Maximum seconds to wait for a solution (default: 120).
    polling_interval: Seconds between status polls (default: 5).

Returns:
    {"success": True, "solution": {...}} on success.
    {"success": False, "error": "...", "error_id": ..., "error_code": "...", "http_status": ...} on failure.

Input parameters:

- `captcha_type` (string, required)
- `cdata`
- `enterprise`
- `invisible`
- `min_score`
- `page_action`
- `polling_interval`
- `proxy`
- `s_token`
- `timeout`
- `user_agent`
- `version`
- `website_key` (string, required)
- `website_url` (string, required)

### `detect_captchas` (~126 tokens)

Detect which captcha types are present on a given page URL.

Opens the page in a headless browser and inspects the DOM to identify
captcha widgets (reCAPTCHA, Cloudflare Turnstile).
Requires playwright to be installed.

Args:
    page_url: The full URL of the page to inspect.

Returns:
    {"success": True, "url": "...", "detected_captchas": ["reCaptchaV2", ...]} on success.
    {"success": False, "error": "..."} on failure.

Input parameters:

- `page_url` (string, required)

### `solve_on_page` (~213 tokens)

Detect, solve, and optionally autofill all captchas on a page.

One-shot operation: opens the page in a headless browser, detects captcha
widgets, solves them via the CapSolver API, and injects the solution tokens
back into the page DOM.

Requires playwright to be installed.

Args:
    page_url: The full URL of the page containing captchas.
    autofill: If True, inject solved tokens into the page (default: True).
    timeout: Maximum seconds to wait per captcha (default: 120).
    polling_interval: Seconds between status polls (default: 5).

Returns:
    {"success": True, "url": "...", "results": [{"captcha_type": "...", "solved": true, "token": "...", "filled": true}, ...]}
    {"success": False, "error": "..."} on failure.

Input parameters:

- `autofill` (boolean)
- `page_url` (string, required)
- `polling_interval`
- `timeout`

### `get_balance` (~65 tokens)

Get the current CapSolver account balance.

Returns:
    {"success": True, "balance": 5.67, "packages": [...]} on success.
    {"success": False, "error": "...", "error_id": ..., "error_code": "..."} on failure.

### `get_supported_captchas` (~38 tokens)

List all captcha types supported by this CapSolver instance.

Returns the registered handler names and all available captcha type values.
No parameters required.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/capsolver-ai-capsolver-mcp/capsolver-mcp#diagnostics

## Score history

- 2026-09-20: 67
- 2026-09-19: 66
- 2026-09-18: 66
- 2026-09-17: 65

## Common questions

### What is the io.github.capsolver-ai/capsolver-mcp server?

io.github.capsolver-ai/capsolver-mcp is listed in the public MCP registry as io.github.capsolver-ai/capsolver-mcp. MCP Server for CapSolver - captcha-solving capabilities for AI agents. This page covers its PyPI package (capsolver-mcp).

### Is the io.github.capsolver-ai/capsolver-mcp server safe to use?

io.github.capsolver-ai/capsolver-mcp scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 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.capsolver-ai/capsolver-mcp server expose?

io.github.capsolver-ai/capsolver-mcp exposes 5 tools: solve_captcha, detect_captchas, solve_on_page, get_balance, get_supported_captchas. Their descriptions and schemas cost roughly 878 tokens of context every time the server is loaded.

### Is the io.github.capsolver-ai/capsolver-mcp server still maintained?

io.github.capsolver-ai/capsolver-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

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