# Sieve (remote · sieve.clawhard.com)

Run regexes on real engines (JavaScript, RE2/Go) against test strings, and prove ReDoS safety.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `sieve.clawhard.com`: 66/100 (this document), [markdown](https://verifymcp.io/servers/com-clawhard-sieve/sieve.md), [page](https://verifymcp.io/servers/com-clawhard-sieve/sieve)

## Channel facts

- Endpoint: `https://sieve.clawhard.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 71/100
  - 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 1574 tokens (~393/item across 4 items; 2 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 2 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**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Sieve MCP server?

Sieve is a hosted endpoint at https://sieve.clawhard.com/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 com-clawhard-sieve 'https://sieve.clawhard.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-clawhard-sieve": {
      "url": "https://sieve.clawhard.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-clawhard-sieve": {
      "type": "http",
      "url": "https://sieve.clawhard.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-clawhard-sieve]
url = "https://sieve.clawhard.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-clawhard-sieve": {
      "type": "remote",
      "url": "https://sieve.clawhard.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-clawhard-sieve --url 'https://sieve.clawhard.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-clawhard-sieve:
    url: "https://sieve.clawhard.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-clawhard-sieve": {
      "Transport": "http",
      "Url": "https://sieve.clawhard.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-clawhard-sieve -t streamable-http -u 'https://sieve.clawhard.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-clawhard-sieve": {
      "type": "http",
      "url": "https://sieve.clawhard.com/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.

### 2026-11-21 (score 66, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-20 (score 66)

First indexed and scored.

## MCP tools (2)

### `sieve_test_regex` (~987 tokens)

Run a regular expression on test strings (JavaScript or RE2/Go) and check it for ReDoS

Use when you have written, been given or are about to commit a regular expression and need to know what it really matches, instead of predicting it (signals: "write a regex for", "does this regex match", "validate emails/phone numbers/dates/slugs/URLs with a regex", "why doesn't my regex match", "test this pattern", "regex for Go", "is this regex safe", "catastrophic backtracking", "convert this Python regex to JavaScript"). Executes the pattern on the real engine: JavaScript (V8 RegExp, the engine in Chrome, Node.js and Cloudflare Workers; flags d g i m s u v y) or RE2 (re2js, with Go regexp parity: Go, RE2, Google Sheets and BigQuery syntax; flags i m s). Give strings that must match and strings that must not; each case comes back pass/fail with the matched text, index and capture groups (numbered and named), and why a "should not match" string matched (usually a missing ^...$). match: "full" tests the whole string. texts lists every match, replace_with shows the replacement ($1/$<name> in JavaScript, $1/${name} in Go). For JavaScript it also runs a ReDoS analysis (recheck): proven linear, or exponential/polynomial backtracking with a concrete attack string and the hot part of the pattern. Flags patterns that compile but mislead: ^a|b$ anchoring, \A/\Z/\h read as letters, [[:alpha:]], {,3}, [A-z], unescaped dots before extensions. Invalid patterns return the engine's error and a hint (Python (?P<name>), (?i), possessive and atomic groups; lookarounds and backreferences in RE2). Example: {"pattern":"[\\w.+-]+@[\\w-]+\\.[a-z]{2,}","should_match":["ann@example.com"],"should_not_match":["ann@example","see ann@x.io now"]}. Does not run Python, PCRE, Java or .NET engines; it reports what differs for common constructs. Up to 100 strings of 20000 characters; on a ReDoS-vulnerable pattern, long strings are skipped instead of hanging. Returns {valid, verdict: ok|warnings|redos|fails|invalid, summary, engine, engine_name, pattern, flags, match_mode, counts:{should_match, sh…

Input parameters:

- `check_redos` (boolean): Run the ReDoS analysis (JavaScript engine). Default true.
- `engine` (string): "javascript" (default; also TypeScript, Node.js, browsers, Deno, Bun) or "re2" (Go regexp, RE2, Google Sheets REGEXMATCH, BigQuery).
- `flags` (string): JavaScript: any of d g i m s u v y. RE2: i m s. Default none.
- `match` (string): "search" (default): a match anywhere counts, like RegExp.test, re.search or Go MatchString. "full": the whole string must match, like Python re.fullmatch.
- `max_matches` (integer): Most matches listed per text (default 10). match_count is always the full count.
- `pattern` (string, required): The regex source, e.g. "^\\d{4}-\\d{2}$" (JSON-escaped), or a JavaScript literal "/^\\d+$/i" (flags then come from the literal).
- `replace_with` (string): Optional replacement; each case also returns the string with every match replaced.
- `should_match` (array): Strings the pattern must match (in match mode).
- `should_not_match` (array): Strings the pattern must not match.
- `texts` (array): Strings to search; every match is listed with its groups (no pass/fail).

### `sieve_check_redos` (~365 tokens)

Check regular expressions for ReDoS (catastrophic backtracking)

Use when a regular expression will run on user input or untrusted data (form validation, request routing, log parsing, WAF or search rules) and must not hang the server, or when reviewing a codebase's regexes for ReDoS (signals: "is this regex safe", "ReDoS", "catastrophic backtracking", "regex hangs", "CPU spike on validation", "security review of regexes", "(a+)+"). Analyzes 1 to 20 patterns with recheck (automaton analysis with a fuzzing fallback) for backtracking engines with JavaScript syntax, and returns per pattern: safe (proven linear, or no attack found when backreferences or lookarounds force fuzzing), or vulnerable with the complexity (exponential, or polynomial with its degree), a concrete attack string (repr like 'a'.repeat(31) + '\\x00', plus the string itself when short), the hot part of the pattern and a fix hint. Example: {"patterns":["^(a+)+$","/^([a-z]+\\s)*$/","^[\\w.+-]+@[\\w-]+\\.[\\w.-]+$"]}. Python re, PCRE, Java, .NET and Ruby backtrack the same way on these constructs; RE2, Go regexp and Rust regex are linear-time and not affected. To also run the pattern on test strings, use sieve_test_regex.

Input parameters:

- `flags` (string): Flags for every pattern given as a raw source (literals keep their own). JavaScript flags d g i m s u v y.
- `patterns` (array, required): Regex sources ("^(a+)+$") or JavaScript literals ("/^(a+)+$/i").

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-clawhard-sieve/sieve#diagnostics

## Score history

- 2026-11-21: 66
- 2026-11-20: 66

## Common questions

### What is the Sieve MCP server?

Sieve is an MCP server listed in the public MCP registry as com.clawhard/sieve. Run regexes on real engines (JavaScript, RE2/Go) against test strings, and prove ReDoS safety. This page covers its hosted endpoint (https://sieve.clawhard.com/mcp).

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

Sieve scores 66 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.

### What tools does the Sieve MCP server expose?

Sieve exposes 2 tools: sieve_test_regex, sieve_check_redos. Their descriptions and schemas cost roughly 1,352 tokens of context every time the server is loaded.

### Does the Sieve MCP server require authentication?

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

### Is the Sieve MCP server still maintained?

Sieve 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 did VerifyMCP test on the Sieve MCP server?

VerifyMCP ran 14 checks on Sieve, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://sieve.clawhard.com/mcp
- Website: https://sieve.clawhard.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-clawhard-sieve/sieve.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-clawhard-sieve/sieve/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-clawhard-sieve/sieve.json
- HTML version of this page: https://verifymcp.io/servers/com-clawhard-sieve/sieve
