// SCAN REPORT

Reqable

35 tools. 12 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

12 can modify or destroy data

23 read-only

35 tools total

Community server · catalogue entry verified 29/06/2026

How to control Reqable ↓

TOOL MAP

What Reqable exposes to your agents

Read (23) Write / Execute (9) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Reqable tools

Destructive · High clear_dry_run_log Clear the dry-run log for a single rule, or for all rules if Destructive · High clear_rules Revoke ALL rules. Use as a panic button when something goes wrong. Destructive · High remove_rule Revoke one rule by id. Returns ``{removed: bool}``. Execute · Medium dry_run_log dry_run_log

12 of Reqable's 35 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Reqable

PolicyLayer is an MCP gateway — it sits between your AI agents and Reqable, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_dry_run_log": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "comment_pattern": {
    "limits": [
      {
        "counter": "comment_pattern_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "auto_token_relay": {
    "limits": [
      {
        "counter": "auto_token_relay_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Reqable — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON REQABLE →

Instant setup, no code required.

FULL CATALOGUE

All 35 Reqable tools

DESTRUCTIVE 3 tools

Destructive clear_dry_run_log Clear the dry-run log for a single rule, or for all rules if Destructive clear_rules Revoke ALL rules. Use as a panic button when something goes wrong. Destructive remove_rule Revoke one rule by id. Returns {removed: bool}.

EXECUTE 2 tools

Execute dry_run_log dry_run_log Execute wait_for wait_for

WRITE 7 tools

Write comment_pattern comment_pattern Write export_har export_har Write export_mitmproxy_flow export_mitmproxy_flow Write patch_body_field patch_body_field Write patch_multipart patch_multipart Write replace_body replace_body Write replace_body_regex replace_body_regex

READ 23 tools

Read auto_token_relay auto_token_relay Read block_request block_request Read decode_body decode_body Read decode_jwt decode_jwt Read diff_requests Field-level diff between two captures. Read dump_body dump_body Read extract_auth extract_auth Read find_dynamic_fields find_dynamic_fields Read get_request get_request Read inject_header inject_header Read list_apps_seen List originating apps observed in the last N minutes. Read list_recent List recently captured requests, newest first. Read list_rules List currently-active rules with hit counts. Read mock_response mock_response Read prettify Decode + pretty-print a body. Read replay_request replay_request Read search_body search_body Read search_url Search captures by URL substring or regex (newest first). Read stats Aggregate stats over the last N minutes. Read status Get reqable-mcp daemon status, schema, and live counters. Read tag_pattern tag_pattern Read to_curl to_curl Read ttl_limits Return {default, max, body_max_bytes} the engine accepts.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Reqable

Can an AI agent delete data through the Reqable MCP server? +

Yes. The Reqable server exposes 3 destructive tools including clear_dry_run_log, clear_rules, remove_rule. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Reqable? +

The Reqable server has 7 write tools including comment_pattern, export_har, export_mitmproxy_flow. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Reqable.

How many tools does the Reqable MCP server expose? +

35 tools across 4 categories: Destructive, Execute, Read, Write. 23 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Reqable? +

Register the Reqable MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Reqable tool call.

Deterministic rules across all 35 Reqable tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON REQABLE →

Instant setup, no code required.

35 Reqable tools catalogued and risk-classified — across an index of 43,000+ MCP servers.