{
  "markdown": "# Sequentum MCP\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nThe [Sequentum MCP Server](https://mcp.sequentum.com) connects your AI coding assistant to Sequentum using the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction), giving your AI tools the ability to create web scraping agents, run management, scheduling, analytics, and more. Sequentum hosts and manages a remote MCP server with OAuth authentication, so there's nothing to install.\n\n## [Tool Reference](./docs/tool-reference.md) | [Prompts Reference](./docs/prompts-reference.md) | [Resources Reference](./docs/resources-reference.md) | [Troubleshooting](./docs/troubleshooting.md) | [Changelog](./CHANGELOG.md)\n\n## Key Features\n\n- **Agent management**: Build, list, search, and get detailed information about your web scraping agents.\n- **Run automation**: Start, stop, and monitor agent executions with real-time status tracking.\n- **Schedule management**: Create and manage automated schedules using cron expressions.\n- **Analytics & diagnostics**: Get run statistics, error analysis, and suggested fixes for failures.\n- **Space organization**: Manage agent workspaces and run batch operations across spaces.\n\n## Disclaimers\n\n`sequentum-mcp` exposes your Sequentum account data to MCP clients, allowing them to\nview, run, and manage your web scraping agents. Keep your credentials secure and avoid\nsharing sensitive information that you don't want accessible to MCP clients.\n\n## Getting Started\n\nAdd the Sequentum MCP server to your client with this configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"sequentum\": {\n      \"url\": \"https://mcp.sequentum.com/mcp\"\n    }\n  }\n}\n```\n\n**Most clients support the OAuth configuration.** Claude.ai and Claude Desktop are simpler still — Sequentum MCP is listed in Claude's connector directory, so there is nothing to enter by hand; see [Claude.ai and Claude Desktop](#claudeai-and-claude-desktop) below. For other clients, when you first connect, you'll be prompted to:\n\n1. Log in with your Sequentum account\n2. Accept the OAuth authorization\n3. Grant access to the necessary permissions\n\nOnce authenticated, all tools become available in your client. For client-specific setup details, see [Set Up Your Client](#set-up-your-client) below.\n\n## Set Up Your Client\n\nSelect your client below for specific setup instructions. All clients use the remote OAuth server at `https://mcp.sequentum.com/mcp` unless noted otherwise.\n\n### Cursor\n\nGo to `Cursor` > `Settings` > `Cursor Settings` > `MCP` and follow the prompts to add the Sequentum MCP server. Cursor 1.0+ includes native OAuth and Streamable HTTP support.\n\nYou can also add the server manually by editing your `mcp.json` file using the [configuration above](#getting-started).\n\n### Claude.ai and Claude Desktop\n\nSequentum MCP is listed in Claude's connector directory, so there is no URL to enter by hand and no custom connector to create.\n\n1. Open **Settings** and go to **Connectors**.\n2. Browse the **Directory**, select **Connectors**, and find **Sequentum MCP**.\n3. Click **Connect** and sign in with your Sequentum account.\n\nTeam and Enterprise workspaces: connector availability is governed at org level, so an admin may need to enable Sequentum MCP before members can connect from their own accounts.\n\n**Enabling per conversation:** once connected, enable Sequentum in an individual conversation via the **+** button near the message composer, then select **Connectors**.\n\n### ChatGPT\n\n> **Note:** While the Sequentum app is pending directory approval, you can connect via Developer Mode. Apps & Connectors → Developer Mode is currently available on **Plus, Pro, Business, Enterprise, and Education** plans (Education is web-only). On Business / Enterprise / Education accounts, only **workspace owners and admins** can access Advanced settings — regular members will not see the option. See [OpenAI's Developer Mode documentation](https://platform.openai.com/docs/developer-mode) for current eligibility.\n\n1. In ChatGPT, go to **Settings** > **Apps & Connectors** > **Advanced settings** and enable **Developer mode**.\n2. Navigate to **Settings** > **Apps & Connectors** and click **Create app** (it appears once Developer mode is enabled).\n3. Enter the connector name `Sequentum` and URL: `https://mcp.sequentum.com/mcp`\n4. Click **Create**. You'll be prompted to sign in with your Sequentum account via OAuth.\n\nOnce connected, enable Sequentum in a conversation via the **+** button near the message composer, then select your connector from the list.\n\n### Claude Code\n\nConnect Sequentum MCP once from the connector directory (see [Claude.ai and Claude Desktop](#claudeai-and-claude-desktop) above) and it is available in Claude Code on the same account.\n\nTo add it directly instead — useful per-project or in scripts:\n\n```bash\nclaude mcp add --transport http sequentum https://mcp.sequentum.com/mcp\n```\n\nThen launch Claude Code with `claude` and type `/mcp` to trigger the OAuth browser flow.\n\n### VS Code / GitHub Copilot\n\nOpen the Command Palette with `Ctrl+Shift+P` (or `Cmd+Shift+P` on macOS) and select `MCP: Add Server`. Enter the Sequentum MCP server URL:\n\n```\nhttps://mcp.sequentum.com/mcp\n```\n\n### Windsurf\n\nConfigure via the `Configure MCP` option in Cascade (`Cmd+L` or `Ctrl+L`). Add the Sequentum MCP server URL:\n\n```\nhttps://mcp.sequentum.com/mcp\n```\n\n### Other Clients\n\nThe Sequentum MCP Server follows standard MCP protocols and works with any client that supports:\n\n- **OAuth authentication** (recommended)\n- **Streamable HTTP** with automatic SSE fallback\n\nUse the server URL `https://mcp.sequentum.com/mcp` in your client's MCP configuration.\n\nThe server supports [Client ID Metadata Documents (CIMD)](https://datatracker.ietf.org/doc/html/draft-ietf-oauth-client-id-metadata-document-00) as the preferred client identification method, with [Dynamic Client Registration (RFC 7591)](https://datatracker.ietf.org/doc/html/rfc7591) as a fallback. MCP clients that support CIMD (such as Cursor) can use their own URL as a `client_id` without any prior registration.\n\n## Deprecated: stdio and API-key auth\n\n> **Deprecated:** Running the MCP server locally over the **stdio** transport,\n> authenticated with `SEQUENTUM_API_KEY`, is deprecated and will be removed in a future\n> release. The `sequentum-mcp` npm package is deprecated along with it. Connect to\n> `https://mcp.sequentum.com/mcp` over HTTP with OAuth 2.1 instead — see\n> [Set Up Your Client](#set-up-your-client).\n>\n> This does not affect Sequentum API keys themselves, which remain fully supported for\n> the [REST API](https://docs.sequentum.com/api-reference/authentication).\n\nThe MCP [authorization specification](https://modelcontextprotocol.io/specification/2026-07-28/basic/authorization)\ndirects stdio implementations not to use OAuth, and to take credentials from the\nenvironment instead. Moving the server to OAuth 2.1 therefore retires the stdio path\nalong with it — the two deprecations are one decision, not two.\n\nIf you are running this configuration today, it keeps working — on Node 20 or later:\n\n```json\n{\n  \"mcpServers\": {\n    \"sequentum\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"sequentum-mcp\"],\n      \"env\": {\n        \"SEQUENTUM_API_KEY\": \"sk-your-api-key-here\"\n      }\n    }\n  }\n}\n```\n\nThe API key is created in the [Sequentum Control Center](https://dashboard.sequentum.com)\nunder **Settings** > **API Keys**, and `SEQUENTUM_API_URL` overrides the Sequentum\ninstance it connects to (default `https://dashboard.sequentum.com`).\n\nTo migrate, delete that block and follow the setup instructions for your client above.\nIf you need Sequentum MCP somewhere that cannot reach `mcp.sequentum.com`, contact\nsupport — there is no supported self-hosted deployment.\n\n## Example Usage\n\nOnce connected, try these prompts to start using Sequentum context in your AI assistant:\n\n```\nWhat agents ran yesterday?\nRun agent <agent name> now.\nIs agent <agent name> still running?\nWhat agents are scheduled to run today?\nDownload the extracted data from agent <agent name>.\nHow many records were found the last time <agent name> was run?\nWhat is my current balance?\nWhich agents cost the most this month?\nSchedule agent <agent name> to run every Monday at 9am.\nLook at the run log for <agent name> run at 9:22am. What caused the agent to fail?\nShow me the cost breakdown for agent <agent name> in January.\nWhat were the most expensive runs for agent <agent name>?\nHow much did I spend on server time vs exports last week?\n```\n\n## Available Tools\n\nThe Sequentum MCP Server provides 39 tools across 9 categories for interacting with the Sequentum platform. See the [Tool Reference](./docs/tool-reference.md) for detailed documentation.\n\n<!-- BEGIN AUTO GENERATED TOOLS -->\n\n- **Agent Management** (3 tools)\n  - [`list_agents`](docs/tool-reference.md#list_agents)\n  - [`get_agent`](docs/tool-reference.md#get_agent)\n  - [`search_agents`](docs/tool-reference.md#search_agents)\n- **Run Management** (6 tools)\n  - [`get_agent_runs`](docs/tool-reference.md#get_agent_runs)\n  - [`get_run_status`](docs/tool-reference.md#get_run_status)\n  - [`start_agent`](docs/tool-reference.md#start_agent)\n  - [`stop_agent`](docs/tool-reference.md#stop_agent)\n  - [`kill_agent`](docs/tool-reference.md#kill_agent)\n  - [`delete_run`](docs/tool-reference.md#delete_run)\n- **File Management** (2 tools)\n  - [`get_run_files`](docs/tool-reference.md#get_run_files)\n  - [`get_file_download_url`](docs/tool-reference.md#get_file_download_url)\n- **Version Management** (2 tools)\n  - [`get_agent_versions`](docs/tool-reference.md#get_agent_versions)\n  - [`restore_agent_version`](docs/tool-reference.md#restore_agent_version)\n- **Schedule Management** (8 tools)\n  - [`list_agent_schedules`](docs/tool-reference.md#list_agent_schedules)\n  - [`get_agent_schedule`](docs/tool-reference.md#get_agent_schedule)\n  - [`create_agent_schedule`](docs/tool-reference.md#create_agent_schedule)\n  - [`update_agent_schedule`](docs/tool-reference.md#update_agent_schedule)\n  - [`enable_agent_schedule`](docs/tool-reference.md#enable_agent_schedule)\n  - [`disable_agent_schedule`](docs/tool-reference.md#disable_agent_schedule)\n  - [`delete_agent_schedule`](docs/tool-reference.md#delete_agent_schedule)\n  - [`get_scheduled_runs`](docs/tool-reference.md#get_scheduled_runs)\n- **Billing & Credits** (6 tools)\n  - [`get_credits_balance`](docs/tool-reference.md#get_credits_balance)\n  - [`get_spending_summary`](docs/tool-reference.md#get_spending_summary)\n  - [`get_credit_history`](docs/tool-reference.md#get_credit_history)\n  - [`get_agents_usage`](docs/tool-reference.md#get_agents_usage)\n  - [`get_agent_cost_breakdown`](docs/tool-reference.md#get_agent_cost_breakdown)\n  - [`get_agent_runs_cost`](docs/tool-reference.md#get_agent_runs_cost)\n- **Space Management** (5 tools)\n  - [`list_spaces`](docs/tool-reference.md#list_spaces)\n  - [`get_space`](docs/tool-reference.md#get_space)\n  - [`get_space_agents`](docs/tool-reference.md#get_space_agents)\n  - [`search_space_by_name`](docs/tool-reference.md#search_space_by_name)\n  - [`run_space_agents`](docs/tool-reference.md#run_space_agents)\n- **Analytics & Diagnostics** (4 tools)\n  - [`get_runs_summary`](docs/tool-reference.md#get_runs_summary)\n  - [`get_records_summary`](docs/tool-reference.md#get_records_summary)\n  - [`get_run_diagnostics`](docs/tool-reference.md#get_run_diagnostics)\n  - [`get_latest_failure`](docs/tool-reference.md#get_latest_failure)\n- **Agent Builder** (3 tools)\n  - [`start_agent_build`](docs/tool-reference.md#start_agent_build)\n  - [`get_agent_build_status`](docs/tool-reference.md#get_agent_build_status)\n  - [`stop_agent_build`](docs/tool-reference.md#stop_agent_build)\n\n<!-- END AUTO GENERATED TOOLS -->\n\n## Available Prompts\n\nThe server includes 9 reusable prompt templates that guide the AI through common multi-step workflows. See the [Prompts Reference](./docs/prompts-reference.md) for detailed documentation.\n\n<!-- BEGIN AUTO GENERATED PROMPTS -->\n\n- **Debugging & Diagnostics**\n  - [`debug-agent`](docs/prompts-reference.md#debug-agent) -- Diagnose why an agent is failing\n  - [`compare-runs`](docs/prompts-reference.md#compare-runs) -- Compare last successful vs failed run\n- **Health & Monitoring**\n  - [`agent-health-check`](docs/prompts-reference.md#agent-health-check) -- Comprehensive health overview for an agent\n  - [`daily-operations-report`](docs/prompts-reference.md#daily-operations-report) -- Daily ops report across all agents\n  - [`space-overview`](docs/prompts-reference.md#space-overview) -- Overview of all agents in a space\n- **Execution**\n  - [`run-and-monitor`](docs/prompts-reference.md#run-and-monitor) -- Start an agent and monitor until completion\n  - [`schedule-agent`](docs/prompts-reference.md#schedule-agent) -- Walk through creating a schedule\n- **Billing & Costs**\n  - [`spending-report`](docs/prompts-reference.md#spending-report) -- Spending and credits report\n  - [`cost-analysis`](docs/prompts-reference.md#cost-analysis) -- Analyze costs across agents\n- **Agent Building**\n  - [`build-agent-from-prompt`](docs/prompts-reference.md#build-agent-from-prompt) -- Build a new agent from a natural language description\n  - [`inspect-agent-draft`](docs/prompts-reference.md#inspect-agent-draft) -- Inspect a build session and decide whether to save or discard\n\n<!-- END AUTO GENERATED PROMPTS -->\n\n## Available Resources\n\nThe server exposes 18 read-only resources (7 static + 11 templates) that AI clients can browse and pull into context. See the [Resources Reference](./docs/resources-reference.md) for detailed documentation.\n\n<!-- BEGIN AUTO GENERATED RESOURCES -->\n\n- **Static Resources** (7)\n  - [`sequentum://agents`](docs/resources-reference.md#agent-list) -- First page of all agents\n  - [`sequentum://spaces`](docs/resources-reference.md#spaces) -- All accessible spaces\n  - [`sequentum://billing/balance`](docs/resources-reference.md#credits-balance) -- Current credits balance\n  - [`sequentum://billing/spending`](docs/resources-reference.md#monthly-spending) -- Monthly spending summary\n  - [`sequentum://billing/agents-usage`](docs/resources-reference.md#agent-costs-current-month) -- Top agents by cost\n  - [`sequentum://analytics/runs`](docs/resources-reference.md#recent-runs-summary) -- Runs in the last 24 hours\n  - [`sequentum://analytics/upcoming-schedules`](docs/resources-reference.md#upcoming-schedules) -- Scheduled runs for next 7 days\n- **Resource Templates** (11)\n  - [`sequentum://agents/{agentId}`](docs/resources-reference.md#agent-detail) -- Agent detail with configuration\n  - [`sequentum://agents/{agentId}/versions`](docs/resources-reference.md#agent-versions) -- Agent version history\n  - [`sequentum://agents/{agentId}/schedules`](docs/resources-reference.md#agent-schedules) -- Agent scheduled tasks\n  - [`sequentum://agents/{agentId}/cost-breakdown`](docs/resources-reference.md#agent-cost-breakdown) -- Agent cost by usage type\n  - [`sequentum://agents/{agentId}/runs`](docs/resources-reference.md#agent-runs) -- Agent run history\n  - [`sequentum://agents/{agentId}/runs/{runId}`](docs/resources-reference.md#run-status) -- Specific run status\n  - [`sequentum://agents/{agentId}/runs/{runId}/files`](docs/resources-reference.md#run-files) -- Run output files\n  - [`sequentum://agents/{agentId}/runs/{runId}/diagnostics`](docs/resources-reference.md#run-diagnostics) -- Run error diagnostics\n  - [`sequentum://agents/{agentId}/latest-failure`](docs/resources-reference.md#latest-failure) -- Most recent failure diagnostics\n  - [`sequentum://spaces/{spaceId}`](docs/resources-reference.md#space-detail) -- Space details\n  - [`sequentum://spaces/{spaceId}/agents`](docs/resources-reference.md#space-agents) -- Agents in a space\n\n<!-- END AUTO GENERATED RESOURCES -->\n\n## Troubleshooting\n\n| Error | Solution |\n|-------|----------|\n| OAuth login not opening | Ensure your client supports OAuth and Streamable HTTP. Try restarting the client. For Claude.ai and Claude Desktop, connect from the [connector directory](#claudeai-and-claude-desktop) rather than a config file. |\n| Connection refused | Verify the URL is `https://mcp.sequentum.com/mcp` and check your network connection. |\n| `SEQUENTUM_API_KEY required` | [Deprecated](#deprecated-stdio-and-api-key-auth) local stdio mode only. Add your API key to the `env` section of the MCP config, or migrate to the hosted server. |\n| `API Error 401: Unauthorized` | Your API key or OAuth token is invalid or expired. Re-authenticate or generate a new key. |\n| `API Error 404: Not Found` | The agent, run, or file doesn't exist, or you don't have access to it. |\n| `API Error 429: Too Many Requests` | Rate limit exceeded. Wait a moment and try again. |\n\nFor more troubleshooting help, see the [Troubleshooting Guide](./docs/troubleshooting.md).\n\n## HTTP Mode Configuration\n\nThe hosted server at `mcp.sequentum.com` runs the Streamable HTTP transport\n(`TRANSPORT_MODE=http`) behind its own deployment configuration. The following\nenvironment variables tune caching, rate limiting, and proxy trust for that transport;\nthey have no effect in the deprecated stdio mode. They are documented for readers of\nthis source — there is no supported self-hosted deployment, and no container image is\npublished.\n\n**HTTP mode is stateless as of 2.0.0.** There is no `Mcp-Session-Id` header and no\nper-client session state on the server: every request is handled independently by a\nfresh MCP server instance. `GET /mcp` no longer opens an SSE stream — it now returns\n`405 Method Not Allowed` (or `401` first if the request is unauthenticated). `DELETE\n/mcp` is a no-op that always answers `200`, since there is no session left to tear\ndown. `MAX_SESSIONS` is no longer read.\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `TRANSPORT_MODE` | `stdio` | Set to `http` to run the Streamable HTTP transport. The `stdio` default is [deprecated](#deprecated-stdio-and-api-key-auth) and will be removed in a future release; the hosted server sets `http`. |\n| `PORT` | `3000` | HTTP server port. |\n| `SEQUENTUM_API_URL` | `https://dashboard.sequentum.com` | Base URL of the Sequentum API this server proxies to. |\n| `SEQUENTUM_OAUTH_ISSUER` | Value of `SEQUENTUM_API_URL` | This deployment's OAuth issuer identifier, advertised in `/.well-known/oauth-protected-resource`. Must be an absolute `https` URL with no query, fragment or userinfo, and must match the authorization server's `issuer` exactly. Set it only when the API base URL and the public OAuth issuer differ; a malformed value refuses to start. |\n| `MCP_CANONICAL_ORIGIN` | derived from the request `Host` header | This server's resource identifier, used to check the `aud` claim of incoming OAuth tokens. Set it to the public origin, e.g. `https://mcp.sequentum.com`. Only the origin is used — the value is normalised through `new URL(...).origin`, so a trailing slash or a path is harmless, and an `aud` naming any path on this origin is accepted. Unset, or set to a value `new URL` cannot parse, the server warns once at startup and falls back to the caller-supplied `Host`. An `aud` on a different origin is logged, not rejected. |\n| `HOST` | `0.0.0.0` | HTTP server bind address. |\n| `LIST_CACHE_TTL_MS` | `3600000` (1 hour) | Freshness hint (`ttlMs`) attached to cacheable list-shaped results (`tools/list`, `prompts/list`, `resources/list`, `resources/templates/list`, `server/discover`). Must be a non-negative integer string; a malformed value fails fast at startup instead of being silently truncated. |\n| `MCP_RATE_LIMIT_WINDOW_MS` | `60000` (1 minute) | Rate-limit window applied to the `/mcp` endpoint. |\n| `MCP_RATE_LIMIT_MAX` | `100` | Maximum `/mcp` requests per window, per process, per IP. See \"Rate limiting across replicas\" below before scaling horizontally. |\n| `TRUST_PROXY` | `true` | Passed to Express's `trust proxy` setting. Accepts `true`, `false`, a hop count (e.g. `1`), or a comma-separated CIDR/IP allowlist. See \"TRUST_PROXY and rate-limit evasion\" below — the default has a known weakness. |\n| `REQUIRE_AUTH` | `true` | Set to `false` to bypass the OAuth Bearer-token requirement on `/mcp`. For local testing only: the connection succeeds, but tools still fail without a valid backend token. |\n\n### Rate limiting across replicas\n\nThe rate limiter is per-process and keyed on `req.ip`; it holds no state shared across\nreplicas. With the stateless transport there is no session affinity, so a given\nclient's requests are not pinned to one replica — in a horizontally scaled deployment\nof N replicas behind a load balancer, the effective cluster-wide ceiling becomes `N ×\nMCP_RATE_LIMIT_MAX` per window, not `MCP_RATE_LIMIT_MAX`. To hold a specific global\nrate, divide `MCP_RATE_LIMIT_MAX` by your replica count.\n\n### TRUST_PROXY and rate-limit evasion\n\nWith the default `TRUST_PROXY=true`, Express trusts every proxy hop and resolves\n`req.ip` from the client-supplied, leftmost entry of the `X-Forwarded-For` header.\nBecause the rate limiter keys on `req.ip`, a client that simply rotates that header\nvalue can evade rate limiting entirely. Running behind a reverse proxy does not fix\nthis by itself: tunnels such as cloudflared and ngrok **append** to `X-Forwarded-For`\nrather than overwrite it, so the attacker-controlled leftmost entry survives unless\n`TRUST_PROXY` is configured correctly.\n\nThe remediation is to set `TRUST_PROXY` to the exact number of trusted reverse-proxy\nhops in front of the server (e.g. `1`), or to a comma-separated CIDR/IP allowlist of\nyour trusted proxies, so Express derives `req.ip` from the correct hop instead of\ntrusting a client-supplied header. This repository does not know your deployment\ntopology, so it deliberately does not choose a safer default for you.\n\n**Severity:** this is an abuse/DoS-protection bypass, not an authentication or data\nexposure issue — no account data is exposed, and no tool call succeeds that would\notherwise be rejected. It only lets a client avoid being rate-limited.\n\n## CORS Origin Allowlist\n\nWhen the MCP server is accessed from a browser (e.g. the Claude web app or the ChatGPT connector), it checks the `Origin` header against an allowlist.  By default the following origins are permitted:\n\n- `https://claude.ai`, `https://claude.com`, and all subdomains (e.g. `team.claude.ai`)\n- `https://chatgpt.com`, `https://platform.openai.com`, and all subdomains under `chatgpt.com` (e.g. `connector.chatgpt.com`)\n- `https://dashboard.sequentum.com`\n- `https://mcp.sequentum.com`\n- `http://localhost:<port>`, `http://127.0.0.1:<port>`, and `http://[::1]:<port>` when `DEBUG=1`\n\nTo add your own origins (e.g. an internal dashboard), set the `ALLOWED_ORIGINS` environment variable to a comma-separated list of exact origins:\n\n```\nALLOWED_ORIGINS=\"https://my-dashboard.example.com,https://other.example.com\"\n```\n\nThese origins are **appended** to the defaults — Claude, ChatGPT, and Sequentum access is preserved.  Wildcards and regular expressions are not supported via the env var; if you need a subdomain wildcard, add a `RegExp` entry directly in `src/server/cors.ts`.\n\n> **Note:** `Origin` matching is case-sensitive and does not include a path or query string.  Native MCP clients (Cursor, Claude Desktop, Claude Code) send no `Origin` header and are not affected by this allowlist.\n\n## Privacy Policy\n\nThe Sequentum MCP Server accesses your Sequentum account data — including agent metadata, run history, scheduled tasks, billing information, and output files — solely to fulfill the requests you make through your AI assistant. By default, the MCP server acts as an authenticated proxy between your MCP client and the Sequentum API: request data is forwarded to the API and responses are returned to your client without being persisted or shared with third parties.\n\nOperators may enable verbose request logging via the `DEBUG=1` environment variable for troubleshooting. In that mode the server redacts `Authorization`, `Cookie`, and `x-api-key` headers, but writes request bodies (which may include tool arguments) to stderr. The hosted server at `mcp.sequentum.com` does not run with `DEBUG=1`.\n\nFor the full Sequentum privacy policy, see [https://www.sequentum.com/privacy-policy](https://www.sequentum.com/privacy-policy).\n\n## Links\n\n- [Sequentum MCP Server](https://mcp.sequentum.com)\n- [Sequentum Dashboard](https://dashboard.sequentum.com)\n- [Sequentum API Documentation](https://dashboard.sequentum.com/api-docs/index.html)\n- [Model Context Protocol](https://modelcontextprotocol.io/)\n\n## License\n\nMIT © [Sequentum](https://sequentum.com)\n",
  "bytes": 24611,
  "sha": "754e78e87bce608416c8b9607b3668ee13102e069ee3aa8536256b7876b35f98",
  "repo_slug": "sequentum/sequentum-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_sequentum_mcp_680a0030/readme"
}