Skip to main content
Glama
hajifkd

inspirehep-mcp

by hajifkd

inspirehep_search_by_title

Search high-energy physics literature on INSPIRE-HEP using title keywords to find relevant papers with citation counts, abstracts, and arXiv links.

Instructions

Search INSPIRE-HEP literature by title.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Implementation Reference

  • The main handler function 'inspirehep_search_by_title' decorated with @mcp.tool(). It takes TitleSearchInput params, builds a query using build_title_query, and executes the search via run_search().
    @mcp.tool(
        name="inspirehep_search_by_title",
        annotations={
            "title": "Search INSPIRE-HEP papers by title",
            "readOnlyHint": True,
            "destructiveHint": False,
            "idempotentHint": True,
            "openWorldHint": True,
        },
    )
    async def inspirehep_search_by_title(params: TitleSearchInput) -> dict[str, Any]:
        """Search INSPIRE-HEP literature by title."""
    
        query = build_title_query(params.title, params.large_collaboration, params.year)
        return await run_search(
            query=query,
            limit=params.limit,
            sort_by_citation=params.sort_by_citation,
        )
  • TitleSearchInput Pydantic model defining the input schema with title field (required, 1-300 chars) and inheriting common search parameters from BaseSearchInput (large_collaboration, limit, sort_by_citation, year).
    class TitleSearchInput(BaseSearchInput):
        title: str = Field(
            ...,
            min_length=1,
            max_length=300,
            description="Title keyword or phrase to search.",
        )
  • run_search async helper function that executes the literature search using InspireHEPClient, handles HTTP errors, and returns formatted results with count and records.
    async def run_search(
        *,
        query: str,
        limit: int,
        sort_by_citation: bool,
        client: InspireHEPClient | None = None,
    ) -> dict[str, Any]:
        sort = _to_inspire_sort(sort_by_citation)
        try:
            if client is not None:
                search_result = await client.search_literature(query=query, limit=limit, sort=sort)
            else:
                async with InspireHEPClient() as default_client:
                    search_result = await default_client.search_literature(
                        query=query,
                        limit=limit,
                        sort=sort,
                    )
        except httpx.HTTPStatusError as exc:
            status = exc.response.status_code
            message = exc.response.text or "No response body."
            raise RuntimeError(
                f"INSPIRE API error ({status}): {message[:300]}"
            ) from exc
        except httpx.HTTPError as exc:
            raise RuntimeError(f"INSPIRE API request failed: {exc}") from exc
    
        return {
            "count": len(search_result.records),
            "records": search_result.records,
        }
  • build_title_query function that constructs an INSPIRE-HEP title search query by escaping the title and applying optional filters (large_collaboration, year).
    def build_title_query(title: str, large_collaboration: bool, year: int | None = None) -> str:
        escaped = _escape_quotes(title)
        base_query = f'title "{escaped}"'
        return _apply_filters(base_query, large_collaboration, year)
  • Helper functions _escape_quotes (line 184-185) and _apply_filters (line 188-194) that sanitize input and add year/author-count filters to the search query.
    def _escape_quotes(value: str) -> str:
        return value.replace("\\", "\\\\").replace('"', '\\"')
    
    
    def _apply_filters(base_query: str, large_collaboration: bool, year: int | None) -> str:
        clauses = [base_query]
        if year is not None:
            clauses.append(f"year {year}")
        if not large_collaboration:
            clauses.append(f"ac 1->{DEFAULT_NON_COLLAB_MAX_AUTHORS}")
        return " and ".join(clauses)

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/hajifkd/inspirehep-mcp'

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