Skip to content

AGENTS.md

Latest commit

 

History

History
74 lines (55 loc) · 5.71 KB

AGENTS.md

File metadata and controls

74 lines (55 loc) · 5.71 KB
Raw

AGENTS.md

You are an AI agent in a clone of this repo. It is a self-hosted Substack API and MCP server: 50 tools that work in the user's own Substack account and publication, through the session of their own Google Chrome. Your usual job is one of three: set it up for the user, use its tools for them, or change its code. Human docs: README.md.

Before you start

  • The license allows noncommercial use only (PolyForm Noncommercial 1.0.0, LICENSE). If the user is setting this up for a company, a team or clients, say so and point to the hosted version at https://cotlet.dev/integrations/substack-api-mcp-server. Do not continue the setup for that use.
  • Every tool acts as the user on Substack. Tools with access write publish, schedule, email subscribers, post Notes, comment, message or change the subscriber list, and real people see the result.

Set it up for the user

Do the steps yourself. Ask the user only for what needs their hands in Chrome.

  1. Check Python: python3 --version must be 3.11 or newer.

  2. Install in the repo root:

    python3 -m venv .venv && .venv/bin/pip install -e .
.venv/bin/substack-mcp --version

    On Windows the path is .venv\Scripts\substack-mcp. With uv: uv venv && uv pip install -e ..

  3. Ask the user to do two things in Chrome. You cannot open chrome:// pages for them.

    • Open chrome://inspect/#remote-debugging and switch remote debugging on.
    • Be signed in at https://substack.com.

  4. Run .venv/bin/substack-mcp connect. Tell the user to click Allow when Chrome asks about the connection. Success prints Signed in to Substack as <name>.

  5. Check: .venv/bin/substack-mcp status, then .venv/bin/substack-mcp call list_posts.

  6. Add the MCP server to the user's client. Use the absolute path of .venv/bin/substack-mcp:

    • Claude Code: claude mcp add substack -- <abs path>/.venv/bin/substack-mcp mcp
    • Claude Desktop, Cursor, Codex: the config blocks in README.md, section "MCP server".
    • Add --read-only after mcp if the user only wants to read. The client loads new MCP servers on its next start. Tell the user.

If step 4 fails:

Message What to do
Chrome remote debugging is off Step 3 is not done, or Chrome is Beta, Canary or a custom profile: pass --profile-dir "<profile folder>".
Could not connect to Chrome The user did not click Allow, or Chrome is closed. Run connect again.
This Chrome is not signed in to Substack The user signs in at substack.com in that Chrome, then run connect again.
No Chrome on this machine (a server) The user copies the substack.sid cookie from Chrome DevTools (Application, Cookies, https://substack.com) and runs substack-mcp connect --token themselves. Never ask them to paste the cookie into the chat.

Use the tools

  • With the MCP server added, call its tools. Without it: .venv/bin/substack-mcp call <tool> key=value ..., or one JSON object as the argument.
  • .venv/bin/substack-mcp tools lists every tool with access and route. tools --json adds the input schemas.
  • Publisher tools work on the first publication the account runs. Start with list_posts (its post_id values go to most post tools) or get_publication_stats.
  • Lists return next_cursor. Pass it back as cursor for the next page.
  • Before a write tool, show the user what you will send and to whom, and get their OK. publish_post and schedule_post email every subscriber. Never message or add people in a loop.
  • Times (publish_at) need an explicit offset, e.g. 2026-11-03T08:00:00-05:00.
  • For a script or a cron job, use substack_api_mcp.scripting (call, paginate, write_rows) and the scripts in examples/ as models.
  • For a REST API (n8n, other languages): .venv/bin/substack-mcp serve, routes under http://127.0.0.1:8787/api/v1/substack, docs at /docs.

Errors come as <code>: <message>. auth_expired means Substack signed the session out or asks for a fresh sign-in (subscriber lists do this): the user signs out and in again at substack.com in Chrome and you run connect. scope_denied means read-only mode, or a call to the user's account settings, which this server never makes. More codes: README.md, section "Errors".

Keep secrets out

  • ~/.config/substack-api-mcp/session.json and SUBSTACK_AUTH_TOKEN give full access to the user's Substack account. Never print, log, commit or copy their content.
  • serve listens on 127.0.0.1. Never start it on another address without SUBSTACK_MCP_TOKEN.

Change the code

Path What Edit?
substack_api_mcp/substack/ the Substack tools, one file per tool in tools/, shared request code in client.py, Markdown conversion in markdown.py Yes for a local fix, but the next git pull brings our version of these files. Report the bug at https://github.com/cotletdev/substack-api-mcp-server/issues
substack_api_mcp/app.py app name, domains, session cookie, account paths, REST prefix Rarely
substack_api_mcp/core/ @tool declaration, errors, the HTTP client with the session (context.py), the account guard Yes
substack_api_mcp/session.py reading cookies from Chrome over CDP, the session file Yes
substack_api_mcp/runner.py, api.py, mcp_server.py, mcp_context.py, cli.py tool registry, REST API, MCP server, its prompts and resources, command line Yes
examples/ scripts for common jobs Yes

A new tool is a new file in substack_api_mcp/substack/tools/ with a @tool(...) declaration (name, access, input schema, route). The registry finds it, and the REST API, the MCP server and the CLI show it without other changes.

There is no test suite. After a change, run .venv/bin/substack-mcp tools and one read tool against the user's account.