Skip to main content
Glama

get_feed

Retrieve Medium articles from recommended, following, or tag-specific feeds. Specify the tab and limit to control the output.

Instructions

Read-only. Reader feed. tab='home' for recommended, 'following', or 'tag-{slug}' (e.g. 'tag-programming').

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tabNohome
limitNo

Implementation Reference

  • Actual handler logic for get_feed. Queries Medium GraphQL: if tab starts with 'tag-', runs TagFeed query by slug; otherwise runs HomeFeed or FollowingFeed query via webFeed. Returns list of post objects (id, title, mediumUrl, clapCount, creator username).
    def get_feed(self, *, tab: str = "home", limit: int = 20) -> list[dict[str, Any]]:
        """Reader feed. tab ∈ {home, following, tag-{slug}}."""
        if tab.startswith("tag-"):
            slug = tab.split("-", 1)[1]
            data = self._gql(
                operation="TagFeed",
                query="""
                query TagFeed($slug: String!, $paging: PagingOptions) {
                  tag(slug: $slug) {
                    name
                    postsConnection(paging: $paging) {
                      edges { node { id title mediumUrl clapCount creator { username } } }
                    }
                  }
                }
                """,
                variables={"slug": slug, "paging": {"limit": limit}},
            )
            edges = (((data.get("tag") or {}).get("postsConnection") or {}).get("edges")) or []
            return [e["node"] for e in edges if e and e.get("node")]
    
        operation = "HomeFeed" if tab == "home" else "FollowingFeed"
        query = """
        query %s($paging: PagingOptions) {
          webFeed(paging: $paging) {
            items {
              post { id title mediumUrl clapCount creator { username } }
            }
          }
        }
        """ % operation
        data = self._gql(
            operation=operation,
            query=query,
            variables={"paging": {"limit": limit}},
        )
        items = ((data.get("webFeed") or {}).get("items")) or []
        return [i.get("post") for i in items if i.get("post")]
  • MCP tool registration metadata for get_feed: description ('Reader feed. tab=home, following, or tag-{slug}') and input_schema (tab string default 'home', limit integer default 20).
    "get_feed": {
        "description": (
            "Read-only. Reader feed. tab='home' for recommended, 'following', or "
            "'tag-{slug}' (e.g. 'tag-programming')."
        ),
        "input_schema": {
            "type": "object",
            "properties": {
                "tab": {"type": "string", "default": "home"},
                "limit": {"type": "integer", "default": 20},
            },
        },
    },
  • Dispatch call in _dispatch() that routes tool name 'get_feed' to MediumClient.get_feed() with tab and limit from args.
    if name == "get_feed":
        return c.get_feed(tab=args.get("tab", "home"), limit=args.get("limit", 20))
  • CLI registration: Typer command 'feed list' that calls c.get_feed(tab=tab, limit=limit).
    @feed_app.command("list")
    def feed_list(
        tab: str = typer.Option("home", "--tab"),
        limit: int = typer.Option(20, "--limit"),
    ) -> None:
        with _client() as c:
            _json(c.get_feed(tab=tab, limit=limit))
  • Test that verifies get_feed is included in the set of expected MCP tools.
    def test_has_core_tools():
        names = set(list_tool_names())
        expected = {
            "test_connection",
            "get_own_profile",
            "get_profile",
            "list_posts",
            "get_post",
            "get_post_content",
            "search_posts",
            "list_responses",
            "get_response_replies",
            "get_feed",
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Declares 'Read-only' upfront, but lacks disclosure on pagination, rate limits, or response structure; no annotations provided so description carries full burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise, single sentence with front-loaded key info ('Read-only') and an example, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose and parameter values adequately for a simple feed tool, but omits output format or error handling; no output schema to compensate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds meaning to the 'tab' parameter by explaining possible values, but does not clarify the 'limit' parameter beyond its default; schema has 0% description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is a 'Reader feed' with specific tab options ('home', 'following', 'tag-{slug}'), distinguishing it from sibling tools like get_post or search_posts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly lists valid tab values with an example, but does not provide when to avoid using this tool or compare to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/06ketan/medium-ops'

If you have feedback or need assistance with the MCP directory API, please join our Discord server