MCP client (Python): guard files with CAIN

1 Get a key

Give each agent its own key in production (console → Agent keys): decisions, trust history and revocation are then per agent.

2 Install

pip install "cainstudio[mcp] @ https://cainstudio.online/cainstudio-0.4.1-py3-none-any.whl#sha256=1bea5cf49aeeb2775acec58933fc39b008a1c84bfd7c9690c54723ed707af689"
export CAIN_API_KEY=...

cainstudio 0.4.1, pinned by URL and SHA-256 so pip installs exactly the published wheel (the package is not on PyPI yet). Framework dependencies come from PyPI as usual.

3 Put CAIN in front of any MCP client session

CainMCPProxy wraps an object with call_tool. A refused call raises or returns the reason before a byte goes to the server. pin_tools records a SHA-256 of each tool's definition and drops a tool that later changes (rug pull); scan_tools drops tools whose description hides instructions (tool poisoning).

from mcp import ClientSession
from cainstudio.integrations.mcp import CainMCPProxy

async with ClientSession(read, write) as session:
    await session.initialize()
    proxy = CainMCPProxy(session, agent_id='files-agent', pin_tools=True, scan_tools=True)
    await proxy.list_tools()      # pins each tool's definition; a changed tool is dropped
    result = await proxy.call_tool('write_file', {"path": "/home/app/.ssh/authorized_keys", "content": "ssh-ed25519 AAAA..."})   # CAIN decides first

On a refusal the agent gets the reason in place of the tool result (or an exception with on_block="raise"). The tool body never runs: not on a refusal, not on a hold, not when CAIN cannot be reached.

4 See what CAIN decides for this exact call

This is the request the integration sends when the model calls write_file with these arguments. record: false evaluates it without writing an evidence record. A new agent has no trust history, so expect REQUIRE_APPROVAL at first; destinations outside your egress allowlist are refused by the egress stage.

5 Write the rule, and test it before you save it

Writing SSH keys is refused; writing to the agent's own output folder runs.

The panel sends the draft rule to the rule tester: it says which rule would decide the call and saves nothing. Swap in the safe arguments below to see it pass through. matches is a case-insensitive glob (*, ?), not a regular expression; conditions on one rule must all hold; the first matching rule by priority wins.

Safe arguments: {"path": "/srv/app/out/report.csv", "content": "a,b"}

When it does what you want, save it from the console or with POST /fabric/tool-rules:

curl -sS -X POST https://cainstudio.online/fabric/tool-rules \
  -H "X-API-Key: $CAIN_API_KEY" -H 'Content-Type: application/json' \
  -d '{"name": "files-guard", "effect": "deny", "priority": 10, "match_path": "/tools/write_file", "conditions": [{"field": "path", "op": "matches", "value": "*/.ssh/*"}]}'

6 Handle the calls that wait for a person

A held call is not executed. It appears in the approval queue with its exact arguments; an approval lets that one call run once. Adapters can wait instead of returning: wait_for_approval=120.

7 Check it before you ship

cainstudio redteam --agent files-agent   # dry-runs dangerous calls; exit 2 if any would run
cainstudio decisions                 # what was decided, and why
cainstudio explain <decision_id>

Every recorded decision is signed; Cain().verify(decision) checks its quorum certificate on your machine (Python SDK).