mirror of
https://github.com/dograh-hq/dograh.git
synced 2026-06-07 07:55:16 +02:00
5762095edf
* feat(mcp): add search_docs tool over Mintlify docs corpus Closes #295. The docs at https://docs.dograh.com promise "Search the Dograh docs for how to configure a TURN server" as an MCP example prompt, but no search_docs tool exists in the MCP server — agents can list workspace resources but cannot search the documentation. This adds a dependency-free, in-process keyword search over the `docs/` tree shipped into the API image (`COPY ./docs ./docs`): - New `api/mcp_server/tools/docs_search.py` — async `search_docs(query, limit=10)` with weighted scoring (path > title > body), a 25-result hard cap, snippet extraction around the first term hit, and graceful empty-list degradation when docs aren't on disk. `DOGRAH_DOCS_PATH` env var overrides location discovery for non-Docker layouts. - Registered in `api/mcp_server/server.py` alongside the other tools, keeping the existing list-alphabetical convention. - `api/tests/test_mcp_docs_search.py` — 18 unit tests covering the pure helpers (tokenizer, frontmatter stripping, title extraction, scoring weights, URL building) and end-to-end ranking, limit clamping, empty-corpus degradation, and input-validation errors. Mocks `authenticate_mcp_request` to avoid the DB dependency, mirroring `test_mcp_save_workflow.py`. Implementation notes: - The docs corpus is ~100 files / ~140k LoC, so a per-call scan runs well under 50 ms; avoiding a vector index / embedding backend keeps the tool zero-dependency and works for fully offline self-hosted deployments. - Authentication is required for consistency with the other MCP tools (and to route through the existing rate-limit middleware), even though docs are not org-scoped data. - Title/path matches deliberately outweigh body matches so a page whose subject IS the query term outranks one that merely mentions it incidentally. * feat: improve docs search --------- Co-authored-by: Abhishek Kumar <abhishek@a6k.me>
43 lines
1.2 KiB
Python
43 lines
1.2 KiB
Python
from fastmcp import FastMCP
|
|
from mcp.types import ToolAnnotations
|
|
|
|
from api.mcp_server.instructions import DOGRAH_MCP_INSTRUCTIONS
|
|
from api.mcp_server.tools.catalog import (
|
|
list_credentials,
|
|
list_documents,
|
|
list_recordings,
|
|
list_tools,
|
|
)
|
|
from api.mcp_server.tools.create_workflow import create_workflow
|
|
from api.mcp_server.tools.docs_search import list_docs, read_doc, search_docs
|
|
from api.mcp_server.tools.get_workflow_code import get_workflow_code
|
|
from api.mcp_server.tools.node_types import get_node_type, list_node_types
|
|
from api.mcp_server.tools.save_workflow import save_workflow
|
|
from api.mcp_server.tools.workflows import get_workflow, list_workflows
|
|
|
|
mcp = FastMCP("dograh", instructions=DOGRAH_MCP_INSTRUCTIONS)
|
|
|
|
for _tool in (
|
|
create_workflow,
|
|
get_node_type,
|
|
get_workflow,
|
|
get_workflow_code,
|
|
list_credentials,
|
|
list_documents,
|
|
list_node_types,
|
|
list_recordings,
|
|
list_tools,
|
|
list_workflows,
|
|
save_workflow,
|
|
):
|
|
mcp.tool(_tool)
|
|
|
|
_DOCS_TOOL_ANNOTATIONS = ToolAnnotations(
|
|
readOnlyHint=True,
|
|
idempotentHint=True,
|
|
destructiveHint=False,
|
|
openWorldHint=False,
|
|
)
|
|
|
|
for _tool in (list_docs, read_doc, search_docs):
|
|
mcp.tool(_tool, annotations=_DOCS_TOOL_ANNOTATIONS)
|