# thinkhard.si prompt tools (remote · thinkhard.si)

669 work prompts, prompt and answer checks, a job planner, a prompt linter and AI prices.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `thinkhard.si`: 80/100 (this document), [markdown](https://verifymcp.io/servers/si-thinkhard-prompt-tools/thinkhard.md), [page](https://verifymcp.io/servers/si-thinkhard-prompt-tools/thinkhard)

## Channel facts

- Endpoint: `https://thinkhard.si/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2613 tokens (~186/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 96% 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 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 thinkhard.si prompt tools MCP server?

thinkhard.si prompt tools is a hosted endpoint at https://thinkhard.si/mcp, so there is nothing to install locally. 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 --transport http si-thinkhard-prompt-tools 'https://thinkhard.si/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "si-thinkhard-prompt-tools": {
      "url": "https://thinkhard.si/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "si-thinkhard-prompt-tools": {
      "type": "http",
      "url": "https://thinkhard.si/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.si-thinkhard-prompt-tools]
url = "https://thinkhard.si/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "si-thinkhard-prompt-tools": {
      "type": "remote",
      "url": "https://thinkhard.si/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add si-thinkhard-prompt-tools --url 'https://thinkhard.si/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  si-thinkhard-prompt-tools:
    url: "https://thinkhard.si/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "si-thinkhard-prompt-tools": {
      "Transport": "http",
      "Url": "https://thinkhard.si/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add si-thinkhard-prompt-tools -t streamable-http -u 'https://thinkhard.si/mcp'
```

### Other

```json
{
  "mcpServers": {
    "si-thinkhard-prompt-tools": {
      "type": "http",
      "url": "https://thinkhard.si/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-05 (score 80, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-04 (score 79, −1)

- [functional regression] Schema quality: 164 → 186
- [functional] Schema quality: excellent → good
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-03 (score 80, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-02 (score 79, 0)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-11-01 (score 79, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-31 (score 78, +1)

- [functional improvement] Tool coverage: 75% → 100%
- [functional] Schema quality: good → excellent
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-30 (score 77, 0)

- [functional regression] Schema quality: 760 → 1139
- [functional regression] Tool coverage: 86% → 75%
- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

### 2026-10-29 (score 77, +1)

- [functional] This server's schema is too large to store in full, so we cannot compare its tools day to day

## MCP tools (14)

The latest capture was truncated, so this tool list may be partial.

### `search_prompts` (~220 tokens)

Input parameters:

- `collection` (string)
- `limit` (integer)
- `model` (string)
- `query` (string, required)

Output parameters:

- `prompts` (array)

### `get_prompt` (~142 tokens)

Input parameters:

- `prompt` (string, required)
- `values` (object)

Output parameters:

- `id` (string)
- `open_blanks` (array)
- `prompt` (string)
- `slug` (string)
- `system` (string)
- `title` (string)
- `url` (string)

### `list_collections` (~27 tokens)

Output parameters:

- `collections` (array)

### `grade_prompt` (~209 tokens)

Input parameters:

- `prompt` (string, required)
- `system` (string)
- `target` (string)

Output parameters:

- `band` (string)
- `checks` (array)
- `engine` (object)
- `score` (integer)
- `target` (string)

### `estimate_ai_cost` (~183 tokens)

Input parameters:

- `calls_per_month` (integer)
- `input_tokens` (integer)
- `models` (array)
- `output_tokens` (integer)
- `prompt_text` (string)

Output parameters:

- `calls_per_month` (integer)
- `checked` (string)
- `input_tokens` (integer)
- `models` (array)
- `output_tokens` (integer)

### `fix_bad_answer` (~154 tokens)

Input parameters:

- `limit` (integer)
- `problem` (string, required)

Output parameters:

- `matches` (array)

### `get_prompt_pattern` (~182 tokens)

Input parameters:

- `limit` (integer)
- `query` (string)

Output parameters:

- `patterns` (array)

### `define_ai_term` (~112 tokens)

Input parameters:

- `limit` (integer)
- `term` (string, required)

Output parameters:

- `terms` (array)

### `check_answer` (~253 tokens)

Input parameters:

- `answer` (string, required)
- `prompt` (string, required)
- `system` (string)
- `target` (string)

Output parameters:

- `answer` (object)
- `facts` (object)
- `has_material` (boolean)
- `rules` (array)
- `summary` (object)
- `tests` (array)

### `build_assistant` (~286 tokens)

Input parameters:

- `actions` (boolean)
- `audience` (string)
- `handoff` (string)
- `knowledge` (string)
- `language` (string)
- `name` (string)
- `never` (string)
- `personal` (boolean)
- `platform` (string)
- `purpose` (string, required)
- `tone` (string)

Output parameters:

- `audience` (string)
- `chars` (integer)
- `description` (string)
- `files` (array)
- `instructions` (string)
- `jobs` (array)
- `name` (string)
- `platform` (object)
- `protected` (integer)
- `protections` (array)
- `protections_total` (integer)
- `sections` (array)
- `settings` (array)
- `starters` (array)
- `tests` (array)
- `topics` (array)
- `warnings` (array)
- `words` (integer)

### `plan_workflow` (~177 tokens)

Input parameters:

- `job` (string, required)
- `material` (string)
- `max_steps` (integer)

Output parameters:

- `gather` (array)
- `steps` (array)
- `summary` (object)
- `values` (object)
- `waves` (array)

### `lint_prompts` (~194 tokens)

Input parameters:

- `code` (string)
- `files` (array)
- `format` (string)
- `path` (string)

Output parameters:

- `catalog_checked` (string)
- `findings` (array)
- `models` (array)
- `prompts` (array)
- `summary` (object)

### `audit_library` (~131 tokens)

Input parameters:

- `prompts` (array)
- `text` (string)

Output parameters:

- `clusters` (array)
- `coverage` (array)
- `distribution` (array)
- `fix_first` (array)
- `gaps` (array)
- `prompts` (array)
- `summary` (object)

### `check_agent_brief` (~200 tokens)

Input parameters:

- `agent` (string)
- `brief` (string, required)
- `repo` (string)

Output parameters:

- `agent` (object)
- `line` (string)
- `parts` (array)
- `readiness` (integer)
- `rewrite` (string)
- `risks` (array)
- `standing` (string)
- `type` (object)
- `words` (integer)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/si-thinkhard-prompt-tools/thinkhard#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 79
- 2026-11-03: 80
- 2026-11-02: 79
- 2026-11-01: 79
- 2026-10-31: 78
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 76
- 2026-10-27: 76
- 2026-10-26: 75
- 2026-10-25: 75
- 2026-10-24: 75
- 2026-10-23: 74

## Common questions

### What is the thinkhard.si prompt tools MCP server?

thinkhard.si prompt tools is an MCP server listed in the public MCP registry as si.thinkhard/prompt-tools. 669 work prompts, prompt and answer checks, a job planner, a prompt linter and AI prices. This page covers its hosted endpoint (https://thinkhard.si/mcp).

### Is the thinkhard.si prompt tools MCP server safe to use?

thinkhard.si prompt tools scores 80 out of 100 on VerifyMCP. 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.

### Does the thinkhard.si prompt tools MCP server require authentication?

No. We connected to thinkhard.si prompt tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the thinkhard.si prompt tools MCP server still maintained?

thinkhard.si prompt tools is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://thinkhard.si/mcp
- Website: https://thinkhard.si/developers/
- Changelog RSS feed: https://verifymcp.io/servers/si-thinkhard-prompt-tools/thinkhard.xml
- Changelog JSON feed: https://verifymcp.io/servers/si-thinkhard-prompt-tools/thinkhard.json
- HTML version of this page: https://verifymcp.io/servers/si-thinkhard-prompt-tools/thinkhard