CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 7s
CI & Build / integration (push) Successful in 16s
CI & Build / TypeScript typecheck (push) Successful in 23s
CI & Build / Python tests (push) Successful in 47s
CI & Build / Build & push image (push) Successful in 28s
_READ_ONLY_TOOLS fails closed, which is the right design — but the list had gone stale, so a read-only key could get_note and not get_snippet, both pure reads of the same table, and could not read a design system at all. That inverts the sensitivity ordering: the free-text records were reachable and the structured, low-sensitivity ones were not. `find_duplicate_snippets` sitting in the list was the tell — someone classified the report and missed the getters beside it. Adds the twelve reads that were missing: snippets, processes, the six design system tools, and list_repo_bindings. Each verified to mutate nothing rather than assumed — this is a security boundary, and a wrong entry does not cost what a missing one costs. record_pulled on four getters is telemetry about the read, not a change to what was read, and get_note already carried it inside the boundary. The list stays explicit. Deriving it from the name would be worse than staleness: it makes the boundary follow a naming convention, so any future get_* grants itself access. list_starter_role_groups is the live illustration — it reads a constant, but names create_design_system in its docstring, so a pattern-matcher flags it. So derive the CANDIDATES and keep the DECISION explicit: a new test asserts every read-shaped tool appears in _READ_ONLY_TOOLS or in a declared _DELIBERATELY_WRITE_SCOPED, and that neither set names a tool that no longer exists. Adding a getter now forces a classification at review time instead of denying it silently. The second set is empty and stays declared — otherwise a future get_or_create_* would be pushed into the allow-list to make the test pass, which is the wrong way to satisfy it. Third instance of the same shape, after #2476 and #2444: a hand-written enumeration that missed the members added after it was written. Refs #2496
160 lines
6.7 KiB
Python
160 lines
6.7 KiB
Python
"""Tests for MCP auth: bearer-token validation that reuses api_keys."""
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from scribe.mcp.auth import resolve_bearer, resolve_bearer_to_user_id
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_bearer_missing_header_returns_none():
|
|
assert await resolve_bearer_to_user_id(None) is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_bearer_malformed_header_returns_none():
|
|
assert await resolve_bearer_to_user_id("Token abc") is None
|
|
assert await resolve_bearer_to_user_id("Bearer") is None
|
|
assert await resolve_bearer_to_user_id("Bearer ") is None
|
|
assert await resolve_bearer_to_user_id("") is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_bearer_unknown_token_returns_none():
|
|
with patch(
|
|
"scribe.mcp.auth.lookup_key",
|
|
AsyncMock(return_value=None),
|
|
):
|
|
assert await resolve_bearer_to_user_id("Bearer fmcp_doesnotexist") is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_bearer_valid_token_returns_user_id():
|
|
fake_key = MagicMock()
|
|
fake_key.user_id = 42
|
|
with patch(
|
|
"scribe.mcp.auth.lookup_key",
|
|
AsyncMock(return_value=fake_key),
|
|
):
|
|
uid = await resolve_bearer_to_user_id("Bearer fmcp_validkey")
|
|
assert uid == 42
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_bearer_calls_lookup_with_stripped_token():
|
|
"""The Bearer prefix and any trailing whitespace must be stripped before lookup."""
|
|
fake_key = MagicMock()
|
|
fake_key.user_id = 1
|
|
mock_lookup = AsyncMock(return_value=fake_key)
|
|
with patch("scribe.mcp.auth.lookup_key", mock_lookup):
|
|
await resolve_bearer_to_user_id("Bearer fmcp_abc123 ")
|
|
mock_lookup.assert_awaited_once_with("fmcp_abc123")
|
|
|
|
|
|
# ── resolve_bearer (user_id + scope) ────────────────────────────────────
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_bearer_returns_user_id_and_scope():
|
|
fake_key = MagicMock()
|
|
fake_key.user_id = 9
|
|
fake_key.scope = "read"
|
|
with patch("scribe.mcp.auth.lookup_key", AsyncMock(return_value=fake_key)):
|
|
assert await resolve_bearer("Bearer fmcp_x") == (9, "read")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_resolve_bearer_none_for_invalid():
|
|
with patch("scribe.mcp.auth.lookup_key", AsyncMock(return_value=None)):
|
|
assert await resolve_bearer("Bearer nope") is None
|
|
assert await resolve_bearer(None) is None
|
|
|
|
|
|
# ── read-only scope gate ────────────────────────────────────────────────
|
|
|
|
def test_body_calls_write_tool_classifies_correctly():
|
|
import json
|
|
from scribe.mcp.server import _body_calls_write_tool
|
|
|
|
def call(name):
|
|
return json.dumps({"jsonrpc": "2.0", "id": 1, "method": "tools/call",
|
|
"params": {"name": name, "arguments": {}}}).encode()
|
|
|
|
# Write-class tools are gated.
|
|
assert _body_calls_write_tool(call("create_note")) is True
|
|
assert _body_calls_write_tool(call("delete_project")) is True
|
|
assert _body_calls_write_tool(call("purge_trash")) is True
|
|
# An unknown/new tool defaults to write (default-deny for read keys).
|
|
assert _body_calls_write_tool(call("brand_new_tool")) is True
|
|
# Read tools and non-call methods pass.
|
|
assert _body_calls_write_tool(call("list_notes")) is False
|
|
assert _body_calls_write_tool(call("get_recent")) is False
|
|
assert _body_calls_write_tool(
|
|
json.dumps({"method": "tools/list"}).encode()
|
|
) is False
|
|
assert _body_calls_write_tool(b"not json") is False
|
|
|
|
|
|
def test_every_read_shaped_tool_is_explicitly_classified():
|
|
"""A read-shaped tool must be classified, not left to default-deny.
|
|
|
|
`_READ_ONLY_TOOLS` is hand-maintained, and default-deny means a getter
|
|
omitted from it fails CLOSED — safe, but silent. That is how a read key
|
|
ended up able to `get_note` and not `get_snippet`, both pure reads of the
|
|
same table, while design systems were unreachable entirely (#2496). The
|
|
`find_duplicate_snippets` entry was the tell: someone classified the report
|
|
and missed the getters beside it.
|
|
|
|
This is the same shape as #2476 (record_pulled on three of four getters) —
|
|
a hand-written enumeration that missed the members added after it. The fix
|
|
there and here is the same: derive the CANDIDATES, keep the DECISION
|
|
explicit. Deriving the decision itself would be worse than a stale list —
|
|
it would make a security boundary follow a naming convention, so any future
|
|
`get_*` grants itself access.
|
|
|
|
So: every tool whose name reads like a read must appear in one of the two
|
|
sets. Adding a getter then forces a choice at review time.
|
|
"""
|
|
import ast
|
|
import pathlib
|
|
|
|
from scribe.mcp.server import _DELIBERATELY_WRITE_SCOPED, _READ_ONLY_TOOLS
|
|
|
|
tools_dir = (pathlib.Path(__file__).resolve().parents[1]
|
|
/ "src" / "scribe" / "mcp" / "tools")
|
|
read_shaped = {
|
|
node.name
|
|
for path in tools_dir.glob("*.py") if path.name != "__init__.py"
|
|
for node in ast.parse(path.read_text()).body
|
|
if isinstance(node, (ast.AsyncFunctionDef, ast.FunctionDef))
|
|
and node.name.startswith(("get_", "list_", "search", "resolve_",
|
|
"check_", "find_"))
|
|
}
|
|
assert read_shaped, "found no read-shaped tools — the tools package moved"
|
|
|
|
unclassified = sorted(read_shaped - _READ_ONLY_TOOLS
|
|
- _DELIBERATELY_WRITE_SCOPED)
|
|
assert not unclassified, (
|
|
f"these read-shaped tools are classified by neither set: {unclassified}. "
|
|
f"They currently fail closed for read-only keys, silently. Add each to "
|
|
f"_READ_ONLY_TOOLS if it mutates nothing, or to "
|
|
f"_DELIBERATELY_WRITE_SCOPED with a comment saying what it writes."
|
|
)
|
|
|
|
# The reverse: a name in either set that no longer exists is a rename or a
|
|
# deletion, and a stale grant is worth surfacing even though it grants
|
|
# access to nothing. `enter_project` is the one read tool without a read
|
|
# prefix, so it is checked against the full tool set, not `read_shaped`.
|
|
all_tools = {
|
|
node.name
|
|
for path in tools_dir.glob("*.py") if path.name != "__init__.py"
|
|
for node in ast.parse(path.read_text()).body
|
|
if isinstance(node, (ast.AsyncFunctionDef, ast.FunctionDef))
|
|
and not node.name.startswith("_") and node.name != "register"
|
|
}
|
|
phantom = sorted((_READ_ONLY_TOOLS | _DELIBERATELY_WRITE_SCOPED) - all_tools)
|
|
assert not phantom, (
|
|
f"these names are classified but are not tools: {phantom}. They were "
|
|
f"renamed or removed — drop them, and check whatever replaced them got "
|
|
f"classified."
|
|
)
|