* added remote MCP server support * trim * added tests * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * increased timeout * disabling MCP chat toggle * Fix MCP OpenAI function-name validation + cancel propagation for PR #5750 OpenAI requires function.name to match ^[a-zA-Z0-9_-]{1,64}$ before streaming starts. The existing 64-char length check is necessary but not sufficient: MCP servers can return tool names containing '.', '/', spaces, etc. that would 400 the whole chat request. Validate the composed mcp__<server_id>__<tool> name against the regex, skip + warn on miss, and drop duplicate tool names from the same server (which would also 400 the request as "duplicates"). Also propagate the agentic-loop cancel_event into MCP tool execution so a /cancel POST during a long-running MCP call (e.g. GitHub MCP search across a large repo) actually interrupts the in-flight HTTP call instead of waiting out the 300 s timeout. The watcher polls the threading.Event at 50 ms cadence inside the asyncio loop (matches routes/inference.py's existing cancel-watcher cadence) and races against the call task with asyncio.wait FIRST_COMPLETED. Tests added: - test_mcp_specs_skip_invalid_openai_function_names: drops bad chars - test_mcp_specs_skip_empty_tool_name - test_mcp_specs_drops_duplicate_names - test_call_tool_sync_respects_pre_set_cancel_event Also fix test_desktop_auth.py's router stub that listed every existing router but missed mcp_servers_router, so importing main.py fails after this PR adds it to routes/__init__.py. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * PR #5750 round 2: OAuth cleanup on delete/url-change + mcp_enabled standalone Round 2 of cross-platform validation surfaced two more P1 findings: 1. OAuth tokens never get cleared. fastmcp keys tokens by MCP URL, not by server row, and delete / URL change / use_oauth toggle only updated the SQLite row. Re-registering the same URL would silently reuse the old account's credentials. Adds clear_oauth_tokens_async() in mcp_client.py and calls it from the delete + put route handlers when the row had use_oauth=True and either the URL changes or OAuth is turned off. 2. mcp_enabled=true was ignored unless the caller also sent enable_tools=true. The frontend always sends both together so the UI path was fine, but a direct API caller sending only mcp_enabled would silently get no MCP tools, which contradicts the field's documented "append tools from every enabled MCP server" behavior. Loosens the use_tools gate in both the GGUF and safetensors paths so mcp_enabled opens the tool loop on its own; when the caller did not also opt into built-ins, the built-in list starts empty. Tests added: - test_clear_oauth_tokens_async_no_op_safe - test_delete_server_calls_oauth_cleanup_when_oauth_was_on - test_delete_server_skips_oauth_cleanup_when_oauth_off - test_update_server_clears_oauth_on_url_change - test_update_server_clears_oauth_when_oauth_disabled 26 backend MCP tests pass; full studio/backend suite 1710 passed locally. Cross-platform CI (Linux, macOS, Windows) green on staging fork. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * PR #5750 round 3: reject null bool updates + /test surfaces 400 Round 3 of cross-platform validation: 1. PUT /api/mcp/servers/<id> would 500 with TypeError when the body explicitly set is_enabled or use_oauth to null. Pydantic accepts None for an Optional[bool] and _changes_from_payload then passed None into mcp_servers_db.update_server, which int(None)d. Reject explicit null at the validation layer with 400 instead. 2. POST /api/mcp/servers/test caught HTTPException under "except Exception", so an invalid URL came back as HTTP 200 with {"ok": false, "error": "400: ..."} instead of a real 400. The create + update paths return 400 for the same input. Move validation outside the transport try/except so it surfaces 400. Tests added: - test_changes_from_payload_rejects_null_is_enabled - test_changes_from_payload_rejects_null_use_oauth - test_test_endpoint_surfaces_url_validation_as_400 * PR #5750 round 4: hyphenated MCP tool names + empty-tool-list gate Round 4 surfaces two more interaction bugs between the new MCP path and existing safetensors tool plumbing: 1. OpenAI accepts ^[a-zA-Z0-9_-]{1,64}$ for function.name, and round 1 widened the MCP regex to that set, so MCP tools can now be advertised as `mcp__srv__list-issues`. But the XML tool-call parser in tool_call_parser.py used `\w+` (no hyphen), so the model could call the tool but Studio could not parse the call. Same in routes/inference.py's `_TOOL_XML_RE` stripper, which would leave hyphenated tool-call XML in the visible content. Both regexes now use `[\w-]+`. 2. safetensors_agentic treats `tools=[]` as "allow all" (documented contract, exercised by test_empty_tools_list_does_not_enforce_allowlist). When a caller sends `enable_tools=true` + `enabled_tools=[]` + `mcp_enabled=true` and MCP discovery returns 0, the resolved tool list is genuinely empty and built-in tools (web_search / python / terminal) could execute via the model's emitted call. Fix at the route gate instead of breaking the documented contract: set `use_tools=False` when the resolved list is empty, in both GGUF and safetensors paths. Existing callers who omit `enabled_tools` still get ALL_TOOLS and are unaffected. Tests added (32 total): - test_tool_xml_parser_handles_hyphenated_function_names - test_tool_xml_strip_handles_hyphenated_function_names - test_safetensors_agentic_empty_allowlist_still_means_allow_all (documents the contract round 4 preserved) 1716 passed locally; cross-platform CI on staging fork still green. * PR #5750 round 5: GGUF allow-list + CLI policy + hyphenated params + cancel race Round 5 of parallel-reviewer aggregation surfaced six additional findings; five are real and fixed here: 1. Hyphenated MCP parameter names (`<parameter=issue-number>`) were dropped by the XML parser's `\w+` regex. Extended to `[\w-]+` in both core/inference/tool_call_parser.py and core/tool_healing.py. The latter is GGUF's own copy of the parser/strip patterns and was missed by round 4. 2. core/tool_healing.py's `strip_tool_call_markup` still used `<function=\w+>` so hyphenated MCP tool-call XML leaked into the GGUF visible content even after round 4 fixed the shared parser. 3+4. `mcp_enabled` re-opened the tool loop even when the operator passed `unsloth run --disable-tools` (CLI policy False). Round 2's `(_tools_on or payload.mcp_enabled)` gate ignored the raw process policy. Now reads `state.tool_policy.get_tool_policy()` and gates mcp_enabled on `_cli_policy is not False`. Applied to both GGUF and safetensors paths. 5. GGUF's agentic loop called `execute_tool(tool_name, ...)` without checking the model-emitted name against the per-request tool list, while the safetensors loop already enforces this. Added the same allow-list check so a model that hallucinates a filtered MCP name or a built-in the caller opted out of returns "not enabled" instead of executing. Bonus P2 fixes: - `call_tool_sync` now checks `cancel_event.is_set()` BEFORE creating the call task, so a pre-set cancellation does not open the HTTP transport. - `clear_oauth_tokens_async` moved the OAuth import + construction inside the protected try block; a fastmcp.client.auth load error used to escape and 500 the delete / update route. NOT fixed (verified false or out of scope): - finding #10 "structured_content vs structuredContent": fastmcp's CallToolResult dataclass uses snake_case (verified live against structured-only tool result; fields are `dict_keys(['content', 'structured_content', 'meta', 'data', 'is_error'])`). - finding #11 "asyncio.run from running loop": call_tool_sync is invoked from `asyncio.to_thread` worker threads which have no event loop; asyncio.run() is safe there. Tests added (37 total): hyphenated param names, tool_healing strip, GGUF allow-list gate, cancel pre-set short-circuit, OAuth cleanup constructor-error swallowing. 1721 passed locally, no regressions. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: danielhanchen <danielhanchen@gmail.com>
223 lines
7.6 KiB
Python
223 lines
7.6 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
import json
|
|
import uuid
|
|
from urllib.parse import urlparse
|
|
|
|
import structlog
|
|
from fastapi import APIRouter, Depends, HTTPException
|
|
|
|
from auth.authentication import get_current_subject
|
|
from core.inference.mcp_client import (
|
|
clear_oauth_tokens_async,
|
|
list_tools_async,
|
|
parse_server_headers,
|
|
)
|
|
from models.mcp_servers import (
|
|
McpServerCreate,
|
|
McpServerProbeResult,
|
|
McpServerResponse,
|
|
McpServerTestRequest,
|
|
McpServerUpdate,
|
|
)
|
|
from storage import mcp_servers_db
|
|
|
|
logger = structlog.get_logger(__name__)
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
_PROBE_TIMEOUT_SECONDS = 8.0
|
|
# When OAuth probes need to open a browser, wait long enough for the user to
|
|
# sign in. Matches fastmcp's default OAuth callback_timeout (300 s) + slack.
|
|
_OAUTH_PROBE_TIMEOUT_SECONDS = 305.0
|
|
|
|
|
|
def _validate_url(url: str) -> str:
|
|
trimmed = (url or "").strip()
|
|
if not trimmed:
|
|
raise HTTPException(status_code = 400, detail = "url must not be empty")
|
|
parsed = urlparse(trimmed)
|
|
if parsed.scheme not in ("http", "https"):
|
|
raise HTTPException(
|
|
status_code = 400,
|
|
detail = "url must start with http:// or https://",
|
|
)
|
|
if not parsed.netloc:
|
|
raise HTTPException(status_code = 400, detail = "url is missing a host")
|
|
return trimmed
|
|
|
|
|
|
def _normalize_headers(headers: dict[str, str] | None) -> dict[str, str] | None:
|
|
"""Trim header names, drop empties, coerce values to str. None if nothing left."""
|
|
if not headers:
|
|
return None
|
|
out: dict[str, str] = {}
|
|
for raw_key, value in headers.items():
|
|
key = str(raw_key).strip()
|
|
if key:
|
|
out[key] = str(value)
|
|
return out or None
|
|
|
|
|
|
def _row_to_response(row: dict) -> McpServerResponse:
|
|
return McpServerResponse(
|
|
id = row["id"],
|
|
display_name = row["display_name"],
|
|
url = row["url"],
|
|
headers = parse_server_headers(row) or {},
|
|
is_enabled = bool(row["is_enabled"]),
|
|
use_oauth = bool(row.get("use_oauth")),
|
|
created_at = row["created_at"],
|
|
updated_at = row["updated_at"],
|
|
)
|
|
|
|
|
|
@router.get("/", response_model = list[McpServerResponse])
|
|
async def list_mcp_servers(
|
|
current_subject: str = Depends(get_current_subject),
|
|
):
|
|
return [_row_to_response(row) for row in mcp_servers_db.list_servers()]
|
|
|
|
|
|
@router.post("/", response_model = McpServerResponse, status_code = 201)
|
|
async def create_mcp_server(
|
|
payload: McpServerCreate,
|
|
current_subject: str = Depends(get_current_subject),
|
|
):
|
|
display_name = (payload.display_name or "").strip()
|
|
if not display_name:
|
|
raise HTTPException(status_code = 400, detail = "display_name must not be empty")
|
|
url = _validate_url(payload.url)
|
|
headers = _normalize_headers(payload.headers)
|
|
|
|
server_id = uuid.uuid4().hex[:16]
|
|
mcp_servers_db.create_server(
|
|
id = server_id,
|
|
display_name = display_name,
|
|
url = url,
|
|
headers_json = json.dumps(headers) if headers else None,
|
|
is_enabled = payload.is_enabled,
|
|
use_oauth = payload.use_oauth,
|
|
)
|
|
return _row_to_response(mcp_servers_db.get_server(server_id))
|
|
|
|
|
|
def _changes_from_payload(payload: McpServerUpdate) -> dict:
|
|
sent = payload.model_fields_set
|
|
changes: dict = {}
|
|
|
|
if "display_name" in sent:
|
|
name = (payload.display_name or "").strip()
|
|
if not name:
|
|
raise HTTPException(
|
|
status_code = 400, detail = "display_name must not be empty"
|
|
)
|
|
changes["display_name"] = name
|
|
if "url" in sent:
|
|
changes["url"] = _validate_url(payload.url or "")
|
|
if "headers" in sent:
|
|
headers = _normalize_headers(payload.headers)
|
|
changes["headers_json"] = json.dumps(headers) if headers else None
|
|
if "is_enabled" in sent:
|
|
if payload.is_enabled is None:
|
|
raise HTTPException(
|
|
status_code = 400, detail = "is_enabled must be true or false"
|
|
)
|
|
changes["is_enabled"] = payload.is_enabled
|
|
if "use_oauth" in sent:
|
|
if payload.use_oauth is None:
|
|
raise HTTPException(
|
|
status_code = 400, detail = "use_oauth must be true or false"
|
|
)
|
|
changes["use_oauth"] = payload.use_oauth
|
|
return changes
|
|
|
|
|
|
@router.put("/{server_id}", response_model = McpServerResponse)
|
|
async def update_mcp_server(
|
|
server_id: str,
|
|
payload: McpServerUpdate,
|
|
current_subject: str = Depends(get_current_subject),
|
|
):
|
|
old = mcp_servers_db.get_server(server_id)
|
|
if not old:
|
|
raise HTTPException(status_code = 404, detail = "MCP server not found")
|
|
changes = _changes_from_payload(payload)
|
|
if not changes:
|
|
raise HTTPException(status_code = 400, detail = "No fields to update")
|
|
# Clear persisted OAuth tokens when the URL changes or OAuth is
|
|
# disabled; fastmcp keys tokens by URL and would otherwise let a
|
|
# re-pointed server silently inherit the old account's credentials.
|
|
if bool(old.get("use_oauth")) and (
|
|
("url" in changes and changes["url"] != old["url"])
|
|
or changes.get("use_oauth") is False
|
|
):
|
|
await clear_oauth_tokens_async(old["url"])
|
|
mcp_servers_db.update_server(server_id, changes)
|
|
return _row_to_response(mcp_servers_db.get_server(server_id))
|
|
|
|
|
|
@router.delete("/{server_id}", status_code = 204)
|
|
async def delete_mcp_server(
|
|
server_id: str,
|
|
current_subject: str = Depends(get_current_subject),
|
|
):
|
|
old = mcp_servers_db.get_server(server_id)
|
|
if not old:
|
|
raise HTTPException(status_code = 404, detail = "MCP server not found")
|
|
if old.get("use_oauth"):
|
|
await clear_oauth_tokens_async(old["url"])
|
|
mcp_servers_db.delete_server(server_id)
|
|
|
|
|
|
@router.post("/{server_id}/refresh", response_model = McpServerProbeResult)
|
|
async def refresh_mcp_server_tools(
|
|
server_id: str,
|
|
current_subject: str = Depends(get_current_subject),
|
|
):
|
|
server = mcp_servers_db.get_server(server_id)
|
|
if not server:
|
|
raise HTTPException(status_code = 404, detail = "MCP server not found")
|
|
|
|
use_oauth = bool(server.get("use_oauth"))
|
|
try:
|
|
tools = await list_tools_async(
|
|
url = server["url"],
|
|
headers = parse_server_headers(server),
|
|
timeout = _OAUTH_PROBE_TIMEOUT_SECONDS
|
|
if use_oauth
|
|
else _PROBE_TIMEOUT_SECONDS,
|
|
use_oauth = use_oauth,
|
|
)
|
|
except Exception as exc: # noqa: BLE001 — surface transport+timeout errors to UI
|
|
logger.warning("MCP refresh failed", server_id = server_id, error = str(exc))
|
|
return McpServerProbeResult(ok = False, error = str(exc))
|
|
|
|
return McpServerProbeResult(ok = True, tool_count = len(tools))
|
|
|
|
|
|
@router.post("/test", response_model = McpServerProbeResult)
|
|
async def test_mcp_server(
|
|
payload: McpServerTestRequest,
|
|
current_subject: str = Depends(get_current_subject),
|
|
):
|
|
# URL/header validation must surface as 400 like create/update so the
|
|
# frontend's create-form pre-flight gets the same error semantics as
|
|
# the actual save call. Only catch transport/timeout errors below.
|
|
url = _validate_url(payload.url)
|
|
headers = _normalize_headers(payload.headers)
|
|
try:
|
|
tools = await list_tools_async(
|
|
url = url,
|
|
headers = headers,
|
|
timeout = _OAUTH_PROBE_TIMEOUT_SECONDS
|
|
if payload.use_oauth
|
|
else _PROBE_TIMEOUT_SECONDS,
|
|
use_oauth = payload.use_oauth,
|
|
)
|
|
except Exception as exc: # noqa: BLE001
|
|
return McpServerProbeResult(ok = False, error = str(exc))
|
|
|
|
return McpServerProbeResult(ok = True, tool_count = len(tools))
|