Reqable MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Reqable MCP Server generate python code for the last POST request to the login endpoint"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Reqable MCP Server
Reqable MCP Server exposes local Reqable capture traffic to MCP clients (Windsurf/Cursor/Claude/Codex).
Default architecture is local-only:
Reqable posts HAR(JSON) to
http://127.0.0.1:18765/report.Optional incremental WebSocket events can be posted to
http://127.0.0.1:18765/ws/events.reqable-mcpnormalizes and stores requests/messages in local SQLite.MCP tools query local data only (no cloud relay by default).
Features
Local-first, privacy-first ingest path.
Real-time ingest via Reqable Report Server.
HAR file import fallback for missed sessions.
HTTP request query/search/domain stats/API analysis.
WebSocket session/message parsing for HAR entries carrying message-frame extensions.
Cross-platform runtime (macOS / Linux / Windows with Python 3.10+).
Related MCP server: ProxyPin MCP Server
Prerequisites
Install and open Reqable.
Configure Reqable Report Server to post to
http://127.0.0.1:18765/report.Ensure Node.js (for
npx) anduv(foruvx) are available.
Installation
Run via npx (recommended)
npx -y reqable-mcp@latestLocal development
uv run reqable-mcpMCP Client Configuration
{
"mcpServers": {
"reqable": {
"command": "npx",
"args": ["-y", "reqable-mcp@latest"]
}
}
}Reqable Report Server Setup
Use these values in Reqable "Add Report Server":
Name:
reqable-mcp-localMatch rule:
*(or your target domains)Server URL:
http://127.0.0.1:18765/reportCompression:
None(or keep consistent with your receiver)
After saving, generate traffic and call ingest_status to verify incoming payload count.
Important note: reqable-mcp still uses HTTP-only ingest transport (no native ws:// listener), but now supports two HTTP ingest paths: /report for HAR/session payload and /ws/events for incremental WebSocket events. WebSocket capture works when Reqable payload includes frame data (for example _webSocketMessages or event frame objects). Raw entry JSON and raw message JSON are preserved and exposed by WebSocket tools. HAR export/import remains the fallback when live pushes miss frames.
Available Tools
ingest_status: ingest server state and countersimport_har: import HAR from file pathlist_requests: list recent HTTP/WebSocket handshake requests with filtersget_request: fetch request details by ID (fullincludesraw_entry)search_requests: keyword search in HTTP URL/body/raw uploaded entry (raw/raw_entry)list_websocket_sessions: list captured WebSocket sessionslist_active_websocket_sessions: list recently active WebSocket sessions by latest captured framesget_websocket_session: fetch WebSocket session details and messages by ID (includingraw_entryand messageraw)tail_websocket_messages: incremental fetch byrequest_id+after_seqcursorsearch_websocket_messages: precise WebSocket message search by keyword, direction, type, opcode, close code, domain, and request IDanalyze_websocket_session: summarize directions, message types, JSON shapes, and close events for a sessionexport_websocket_session_raw: export the raw uploaded WebSocket entry and raw frame listhealth_report: ingest status + WebSocket data quality reportrepair_websocket_messages: backfill missing fields from raw frames (supports dry-run)get_domains: domain-level request statisticsanalyze_api: infer API shapes for a domaingenerate_code: generate sample client code from captured HTTP request
Environment Variables
Variable | Description | Default |
| Report receiver host |
|
| Report receiver port |
|
| Report receiver path |
|
| Incremental WebSocket event receiver path |
|
| Local data directory | platform app data dir |
| SQLite file path |
|
| Max persisted body bytes per request/message |
|
| Max accepted report payload bytes |
|
| Max HAR import file bytes |
|
| Local retention window |
|
| Optional local auth token | unset |
Privacy and Data Retention
Data stays on local machine in default mode.
Retention cleanup is applied to local DB records, including WebSocket messages.
If ingest server is offline, Reqable failed report push is not retried.
License
MIT
Available Tools
17 toolsanalyze_apiC
Analyze API structure for a specific domain.
Inputs: domain (required). Returns: result
analyze_websocket_sessionB
Analyze a WebSocket session and summarize frame directions, types, JSON shapes, and close events.
Inputs: request_id (required), sample_limit. Returns: result
export_websocket_session_rawC
Export the raw uploaded WebSocket session entry and raw frame list.
Inputs: request_id (required), include_normalized. Returns: result
generate_codeC
Generate API call code from a captured request.
Inputs: request_id (required), language, framework. Returns: result
get_domainsB
Get all captured domains with request counts.
Inputs: no named parameters. Returns: result
get_requestB
Get detailed information for a single request.
Inputs: request_id (required), include_body. Returns: result
get_websocket_sessionB
Get WebSocket session details and messages by request ID.
Inputs: request_id (required), include_messages. Returns: result
health_reportC
Return ingest status plus data quality checks for WebSocket payloads.
Inputs: detail, sample_limit. Returns: result
import_harC
Import a HAR file (or line-delimited JSON entries) as fallback.
Inputs: file_path (required). Returns: result
ingest_statusB
Check local ingest server status.
Inputs: auto_start. Returns: result
list_active_websocket_sessionsB
List recently active WebSocket sessions inferred from latest captured frames.
Inputs: limit, domain, active_within_seconds, include_closing. Returns: result
list_requestsC
List recent HTTP/WebSocket handshake requests captured from Reqable reports.
Inputs: limit, detail, domain, method, +1 more. Returns: result
list_websocket_sessionsC
List captured WebSocket sessions.
Inputs: limit, detail, domain. Returns: result
repair_websocket_messagesB
Backfill missing WebSocket message fields from raw frames.
Inputs: max_rows, dry_run. Returns: result
search_requestsB
Search requests by keyword in URL, bodies, or raw uploaded entry (raw / raw_entry).
Inputs: keyword (required), search_in, limit. Returns: result
search_websocket_messagesC
Search WebSocket messages by keyword and precise frame filters.
Inputs: keyword, direction, message_type, opcode, +5 more. Returns: result
tail_websocket_messagesC
Tail WebSocket messages for one session using seq cursor.
Inputs: request_id (required), after_seq, direction, message_type, +2 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools have distinct purposes targeting specific resources like HTTP requests, WebSocket sessions, or data operations, with clear boundaries. However, some overlap exists between list_websocket_sessions and list_active_websocket_sessions, which could cause confusion in selection without careful reading of descriptions.
Tool names follow a highly consistent snake_case pattern with clear verb_noun structures throughout, such as analyze_api, get_request, list_requests, and search_websocket_messages. There are no deviations in naming conventions, making the set predictable and readable.
With 17 tools, the count is slightly high but reasonable for the server's scope in API and WebSocket analysis, covering ingestion, querying, and data management. It feels comprehensive without being overly bloated, though it borders on the heavy side for typical MCP servers.
The tool set provides complete coverage for the domain of API and WebSocket analysis, including ingestion (import_har, ingest_status), querying (list_requests, search_requests), detailed access (get_request, get_websocket_session), analysis (analyze_api, analyze_websocket_session), and data management (export, repair, tail). No obvious gaps are present, supporting full lifecycle workflows.
Maintenance
Related MCP Connectors
An MCP server for search and retrieval over a local LanceDB database
Official MCP server for MAQAMI, a hotel and flight booking platform with 3M+ hotels. Search live hotel rates and flights, look up places, airports and hotel details, then prebook and book. Remote Streamable HTTP endpoint, no API key required.
Capture, inspect & debug HTTPS traffic across iOS, Android, browsers & backends — 304 MCP tools.
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables AI assistants to capture and analyze HTTP/HTTPS traffic from Android devices. It supports smart searching of network requests and provides tools for detailed traffic analysis via natural language.11246MIT
- AlicenseBqualityDmaintenanceExposes ProxyPin's local network capture history to MCP-capable clients for searching, analyzing, and detailing captured HTTP traffic. It enables users to perform API structure analysis and generate client-side code directly from captured requests.628 PyPI17MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to query, filter, and analyze local HTTP capture records and REST API test data from the Reqable tool. It provides read-only access to inspect request/response details, headers, and statistics through natural language.27-
- AlicenseNot gradedqualityDmaintenanceRead-only MCP server that brings Reqable's captured HTTP traffic into Claude Code conversations, enabling querying, searching, waiting for, and analyzing requests without requiring Reqable Pro.7MIT