Medium MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEDIUM_ADDITIONAL_DOMAINS | No | Comma-separated list of additional Medium partner domains (e.g., "stackademic.com,another.com"). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_articleA | Read and extract content from a Medium article URL. Returns the article title, author, content in Markdown format, and metadata. |
| loginA | Open a browser window to log in to Medium. After logging in, use 'save_login' to save your session for accessing member-only content. |
| save_loginA | Save the current login session after completing login in the browser. Must be called after 'login' tool. |
| logoutA | Clear the saved Medium login session. |
| login_statusA | Check if you are currently logged in to Medium. |
| add_domainA | Add a custom Medium partner domain to the allowed list. The domain will be saved to config file. |
| list_domainsA | Show all allowed Medium domains (default + custom + environment) |
| remove_domainA | Remove a custom domain from the allowed list. Cannot remove default domains. |
| list_author_articlesA | Get a list of articles from a Medium author. Uses RSS feed by default (fast, ~10 recent articles with full content). Use source='scrape' for more articles (slower, may trigger bot detection). |
| search_articlesA | Search for articles across all of Medium. Uses web scraping (may trigger bot detection). |
| search_author_articlesA | Search for articles within a specific author's posts. Uses RSS feed (fast, limited to ~10 recent articles). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Most tools target distinct actions (login, domain management, reading, searching). The only potential confusion is between search_author_articles and list_author_articles, but descriptions clarify search (query within author) versus list (full article list). All others are clearly separated by resource and action.
Tool names follow a consistent snake_case verb_noun pattern (e.g., search_articles, add_domain, remove_domain). The only deviation is 'login_status', which uses a noun phrase rather than a verb, but it is still readable and predictable. No mixed casing or chaotic naming.
Eleven tools is well-scoped for a Medium server that handles authentication, article retrieval, author queries, and domain configuration. Each tool covers a distinct feature area without redundancy or bloat.
The server provides solid coverage for reading and searching Medium content, including member-only access via login. Missing writing/publishing and comment features, but these appear out of scope. The domain management tools are a bit niche but complete for their purpose.