GoHighLevel MCP Server — 520+ tools across 40 categories. Voice AI, Proposals, Contacts, Calendars, Conversations, Opportunities, Invoices, Payments, Workflows, Social Media, and more. MCP SDK 1.26, Streamable HTTP, tool annotations.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"ghl-mcp-server": {
"env": {
"GHL_API_KEY": "your_private_integrations_api_key",
"GHL_BASE_URL": "https://services.leadconnectorhq.com",
"GHL_LOCATION_ID": "your_location_id"
},
"args": [
"/absolute/path/to/Go-High-Level-MCP-2026-Complete/dist/server.js"
],
"command": "node"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
🚀 Don't want to self-host? Join the waitlist for our fully managed solution → > Zero setup. Zero maintenance. Just connect and automate.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'clawdbot' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
OpenClaw Telegram allowlist authorization accepted mutable usernames
## Summary Telegram allowlist authorization could match on `@username` (mutable/recyclable) instead of immutable numeric sender IDs. ## Impact Operators who treat Telegram allowlists as strict identity controls could unintentionally grant access if a username changes hands (identity rebinding/spoof risk). This can allow an unauthorized sender to interact with the bot in allowlist mode. ## Affected Packages / Versions - npm `openclaw`: <= 2026.2.13 - npm `clawdbot`: <= 2026.1.24-3 ## Fix Teleg
OpenClaw Google Chat shared-path webhook target ambiguity allowed cross-account policy-context misrouting
## Summary When multiple Google Chat webhook targets are registered on the same HTTP path, and request verification succeeds for more than one target, inbound webhook events could be routed by first-match semantics. This can cause cross-account policy/context misrouting. ## Affected Packages / Versions - npm: `openclaw` <= 2026.2.13 - npm: `clawdbot` <= 2026.1.24-3 ## Details Affected component: `extensions/googlechat/src/monitor.ts`. Baseline behavior allowed multiple webhook targets per pat
OpenClaw affected by cross-site request forgery (CSRF) through loopback browser mutation endpoints
## Summary Browser-facing localhost mutation routes accepted cross-origin browser requests without explicit Origin/Referer validation. Loopback binding reduces remote exposure but does not prevent browser-initiated requests from malicious origins. ## Impact A malicious website can trigger unauthorized state changes against a victim's local OpenClaw browser control plane (for example opening tabs, starting/stopping the browser, mutating storage/cookies) if the browser control service is reachabl
OpenClaw affected by denial of service via unbounded webhook request body buffering
### Summary Multiple webhook handlers accepted and buffered request bodies without a strict unified byte/time limit. A remote unauthenticated attacker could send oversized payloads and cause memory pressure, degrading availability. ### Details Affected packages: - `openclaw` (npm): `<2026.2.12` - `clawdbot` (npm): `<=2026.1.24-3` Root cause: - Webhook code paths buffered request payloads without consistent `maxBytes` + `timeoutMs` enforcement. - Some SDK-backed handlers parse request bodies in
OpenClaw affected by denial of service through unguarded archive extraction allowing high expansion/resource abuse (ZIP/TAR)
## Summary Archive extraction lacked strict resource budgets, allowing high-expansion ZIP/TAR archives to consume excessive CPU/memory/disk during install/update flows. ## Affected Packages / Versions - openclaw (npm): <= 2026.2.13 - clawdbot (npm): <= 2026.1.24-3 ## Details Affected component: `src/infra/archive.ts` (`extractArchive`). The extractor now enforces resource budgets (entry count and extracted byte limits; ZIP also enforces a compressed archive size limit) and rejects over-budget
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in marketing / communication
An MCP server that securely interfaces with your iMessage database via the Model Context Protocol (MCP), allowing LLMs to query and analyze iMessage conversations. It includes robust phone number validation, attachment processing, contact management, group chat handling, and full support for sending and receiving messages.
Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite
DataForSEO API modelcontextprotocol server
MCP server for Kaseya Autotask PSA — 39 tools for companies, tickets, projects, time entries, and more
MCP Security Weekly
Get CVE alerts and security updates for Go High Level MCP 2026 Complete and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Model Context Protocol server for GoHighLevel. It exposes GHL API operations as MCP tools over stdio, Streamable HTTP, and legacy SSE.
576576 / 576238834 (802 raw API tools plus 32 curated agent workflow tools)253Coverage artifacts:
docs/GHL-API-COVERAGE-REPORT.mddocs/GHL-LOCAL-ENDPOINT-CLASSIFICATION.mddocs/ghl-api-coverage.jsondocs/API-DASHBOARD.mddocs/tool-inventory.jsonThe MCP server stays focused on MCP transports and GHL tool execution. Companion tooling lives beside it for setup, inspection, updates, and examples.
npm run tools:doctor # Check build output, env, and API coverage health
npm run tools:list # Browse the registered MCP tool inventory
npm run tools:report # Regenerate the API dashboard and tool inventory JSON
npm run tools:explorer # Print the local static tool explorer path
npm run tools:configure # Print a Claude-compatible MCP config snippet
npm run tools:update-api # Refresh official GHL API coverage and generated tools
Direct CLI usage:
npx ghl-mcp doctor
npx ghl-mcp list-tools --search ads
npx ghl-mcp configure claude
npx ghl-mcp test-tool search_contacts '{"locationId":"your_location_id","pageLimit":1}'
See docs/TOOLING.md for the full tooling map.
By default, the server exposes the full tool surface: raw endpoint tools plus the curated CRM workflow layer. Agents that work better with fewer, higher-level actions can use:
GHL_TOOL_PROFILE=curated npm run start:stdio
Profiles:
full - default; exposes all 834 tools.curated - exposes only the 32 agent workspace tools, such as crm_prepare_lead_intake, crm_prepare_conversation_reply, crm_prepare_appointment_booking, and crm_location_health_check.raw - exposes only the original 802 endpoint-level tools.The curated tools return structured confirmation queues for writes. They stage the exact raw tool calls an agent should execute after the user confirms, instead of making outbound messages, billing, workflow enrollment, stage moves, or snapshot pushes feel like one ambiguous API call.
The examples/ directory turns the tool surface into practical MCP workflows:
examples/recipes/ — structured JSON recipes for lead intake, appointment booking, pipeline follow-up, ads reporting, review requests, location health checks, and more.examples/agents/ — starter assistant prompts for CRM, appointment setting, pipeline management, ads reporting, and agency operations.docs/tool-explorer.html — static browser explorer for docs/tool-inventory.json.Recipes use real MCP tool names and include confirmation points for actions like outbound messages, appointment creation, workflow enrollment, deletes, and snapshot pushes.
mcp-apps/ contains companion MCP Apps for hosts that support interactive MCP resources. They run as a separate app server so the core MCP API server stays lean.
MCP Apps require Node 20+ because they use @modelcontextprotocol/ext-apps.
The apps are wired to the curated CRM workflow tools first, so buttons like "Prepare lead intake," "Prepare booking," and "Prepare snapshot rollout" produce confirmation-gated action plans for ChatGPT, Claude, or another MCP host.
npm run build
npm run apps:install
npm run apps:build
npm run apps:start:stdio
Included app tools:
show_ghl_tool_explorer_appshow_ghl_contact_workspace_appshow_ghl_lead_intake_appshow_ghl_conversation_inbox_appshow_ghl_pipeline_board_appshow_ghl_appointment_desk_app