Files
FabledScribe/tests/test_mcp_auth.py
T
bvandeusenandClaude Opus 5 0bf7406f42
CI & Build / Python lint (push) Successful in 4s
CI & Build / Plugin hooks (push) Successful in 10s
CI & Build / TypeScript typecheck (push) Successful in 53s
CI & Build / integration (push) Successful in 55s
CI & Build / Python tests (push) Successful in 1m40s
CI & Build / Build & push image (push) Successful in 25s
fix(mcp): two rule reads reach a read-only key, and every tool must now be classified (#3191)
rules_due_for_verification (the rule staleness sweep) and rule_history (what a
rule used to say) are pure reads, and a read-scoped API key was refused both:
neither is in _READ_ONLY_TOOLS, and the completeness test that should have
caught it only looked at tools whose NAMES start like a read (get_, list_,
search…). Neither does.

- Both join _READ_ONLY_TOOLS; the comment that pointed at this issue now says
  why they sat unlisted.
- _WRITE_TOOLS declares every writing tool by name. Nothing reads it at
  runtime — default-deny already refuses an unlisted tool — it exists so the
  classification is total.
- test_every_registered_tool_is_classified_exactly_once takes its candidates
  from what build_mcp_server() actually mounts, requires each in exactly one
  of the three sets, and still flags a classified name that is no tool. The
  decision stays explicit; only the candidate set widened.
- test_the_completeness_check_can_fail drops a real tool from its set and
  asserts it is noticed (rule 167).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy
2026-09-15 12:31:04 -04:00

166 lines
6.6 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
@pytest.mark.asyncio
async def test_resolve_bearer_missing_header_returns_none():
assert await resolve_bearer(None) is None
@pytest.mark.asyncio
async def test_resolve_bearer_malformed_header_returns_none():
assert await resolve_bearer("Token abc") is None
assert await resolve_bearer("Bearer") is None
assert await resolve_bearer("Bearer ") is None
assert await resolve_bearer("") 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("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
fake_key.scope = "write"
with patch(
"scribe.mcp.auth.lookup_key",
AsyncMock(return_value=fake_key),
):
uid, scope = await resolve_bearer("Bearer fmcp_validkey")
assert (uid, scope) == (42, "write")
@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
fake_key.scope = "write"
mock_lookup = AsyncMock(return_value=fake_key)
with patch("scribe.mcp.auth.lookup_key", mock_lookup):
await resolve_bearer("Bearer fmcp_abc123 ")
mock_lookup.assert_awaited_once_with("fmcp_abc123")
# ── 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 _registered_tool_names() -> set[str]:
"""What the server actually mounts — not a glob of function names, which
would count helpers and miss anything registered another way."""
from scribe.mcp.server import build_mcp_server
return {tool.name for tool in build_mcp_server()._tool_manager.list_tools()}
def test_every_registered_tool_is_classified_exactly_once():
"""Every tool must be declared a read, a write, or a read-shaped write.
`_READ_ONLY_TOOLS` is hand-maintained, and default-deny means a read
omitted from it fails CLOSED — safe, but silent. That is how a read key
ended up able to `get_note` and not `get_snippet` (#2496), and how
`rules_due_for_verification` and `rule_history` sat denied (#3191).
The fix keeps the DECISION explicit and derives the CANDIDATES. Deriving
the decision would make a security boundary follow a naming convention, so
any future `get_*` grants itself access. This test used to derive
candidates from names too — tools starting `get_`, `list_`, `search`… — and
that narrowing is exactly what let the two #3191 reads through: neither
name looked like a read. So the candidates are now EVERY registered tool.
"""
from scribe.mcp.server import (
_DELIBERATELY_WRITE_SCOPED, _READ_ONLY_TOOLS, _WRITE_TOOLS,
)
registered = _registered_tool_names()
assert len(registered) > 50, "found almost no tools — registration moved"
sets = {
"_READ_ONLY_TOOLS": _READ_ONLY_TOOLS,
"_WRITE_TOOLS": _WRITE_TOOLS,
"_DELIBERATELY_WRITE_SCOPED": _DELIBERATELY_WRITE_SCOPED,
}
unclassified = sorted(registered - set().union(*sets.values()))
assert not unclassified, (
f"these tools are classified by no set: {unclassified}. A read key is "
f"silently denied them. Add each to _READ_ONLY_TOOLS if it mutates "
f"nothing, otherwise to _WRITE_TOOLS."
)
names = list(sets)
for i, first in enumerate(names):
for second in names[i + 1:]:
both = sorted(sets[first] & sets[second])
assert not both, f"in both {first} and {second}: {both}"
# The reverse: a classified name that is not a tool is a rename or a
# deletion, and a stale grant is worth surfacing even though it grants
# access to nothing.
phantom = sorted(set().union(*sets.values()) - registered)
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."
)
def test_the_completeness_check_can_fail():
"""A guard that cannot fail is indistinguishable from one that is broken
(rule 167). Drop a real tool from its set and the check must notice."""
from scribe.mcp.server import _READ_ONLY_TOOLS, _WRITE_TOOLS
registered = _registered_tool_names()
assert "rule_history" in _READ_ONLY_TOOLS
without = (_READ_ONLY_TOOLS - {"rule_history"}) | _WRITE_TOOLS
assert "rule_history" in registered - without