Skip to main content
Glama
ptorsten

humaans-mcp

by ptorsten

get_me

Retrieve the authenticated user associated with the current API token.

Instructions

Return the authenticated user for the current API token.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The get_me tool handler: an async function decorated with @mcp.tool() that calls the Humaans API's /me endpoint via the client and returns the authenticated user info for the current API token.
    @mcp.tool()
    async def get_me() -> dict[str, Any]:
        """Return the authenticated user for the current API token."""
        return await client().get("/me")
  • The tool is registered via the @mcp.tool() decorator on line 28, which makes the get_me function available as an MCP tool.
    @mcp.tool()
  • The HumaansClient class used by get_me. The get() method (lines 34-43) performs the actual HTTP GET request to the Humaans API, which get_me calls with path '/me'.
    class HumaansClient:
        def __init__(self, token: str | None = None):
            token = token or os.environ.get("HUMAANS_API_TOKEN")
            if not token:
                raise RuntimeError("HUMAANS_API_TOKEN environment variable is required")
            self._client = httpx.AsyncClient(
                base_url=BASE_URL,
                headers={"Authorization": f"Bearer {token}"},
                timeout=DEFAULT_TIMEOUT,
            )
    
        async def aclose(self) -> None:
            await self._client.aclose()
    
        async def get(self, path: str, params: dict[str, Any] | None = None) -> Any:
            clean = {k: v for k, v in (params or {}).items() if v is not None}
            resp = await self._client.get(path, params=clean)
            if resp.status_code >= 400:
                try:
                    body = resp.json()
                except Exception:
                    body = resp.text
                raise HumaansError(resp.status_code, path, body)
            return resp.json()
    
        async def list_page(
            self,
            path: str,
            filters: dict[str, Any] | None = None,
            limit: int = 100,
            skip: int = 0,
        ) -> Any:
            params = dict(filters or {})
            params["$limit"] = limit
            params["$skip"] = skip
            return await self.get(path, params)
    
        async def list_all(
            self,
            path: str,
            filters: dict[str, Any] | None = None,
            cap: int = MAX_LIST_ALL,
        ) -> list[dict[str, Any]]:
            collected: list[dict[str, Any]] = []
            skip = 0
            while len(collected) < cap:
                page = await self.list_page(path, filters=filters, limit=PAGE_SIZE, skip=skip)
                items = page.get("data") if isinstance(page, dict) else page
                if not items:
                    break
                collected.extend(items)
                if len(items) < PAGE_SIZE:
                    break
                skip += PAGE_SIZE
            return collected[:cap]
Behavior3/5

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

With no annotations provided, the description carries the full burden. It correctly implies a read-only, authenticated operation, but does not disclose additional behavioral details such as rate limits, authentication requirements (beyond the vague 'for the current API token'), or potential side effects.

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?

A single, front-loaded sentence that directly states purpose with no superfluous words. Every word earns its place.

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

Completeness5/5

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

Given zero parameters and the existence of an output schema (which describes the return type), the description is complete. It succinctly covers what the tool does for the current user context.

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

Parameters4/5

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

The input schema has zero parameters with 100% coverage. Per the calibration, 0 parameters earns a baseline of 4. The description adds meaning by specifying that the 'authenticated user' is the output, which goes beyond the empty schema.

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 'Return the authenticated user for the current API token' clearly states the tool's purpose with a specific verb ('Return') and resource ('authenticated user'). It distinguishes itself from sibling tools like 'get_person' or 'get_company' by focusing on the current user context.

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

Usage Guidelines3/5

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

No explicit guidance on when or when not to use this tool versus alternatives like 'get_person' (which takes an ID). The description implies usage for retrieving the current user, but lacks comparative context or exclusion criteria.

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/ptorsten/humaans-mcp'

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