Blekline | AI Firewall

blekline-client — Python wrapper for the Blekline REST API.

Use the Python SDK when your agent pipeline is Python-based — LangChain, custom orchestrators, data pipelines — and you need masking or tool enforcement outside the MCP stdio path.

Install from the monorepo:

pip install -e packages/client-python

Quick start

import os
from blekline_client import BleklineClient

client = BleklineClient(
    workspace_token=os.environ["BLEKLINE_WORKSPACE_TOKEN"],
    base_url="https://app.blekline.com",
    client_surface="sdk",
)

masked = client.mask(text="Email alice@corp.com my SSN 123-45-6789", platform="Python")
print(masked["maskedText"], masked.get("decision"))

tool = client.enforce_tool_call(
    tool_name="write_file",
    arguments={"path": "/tmp/out.txt", "content": "sk-proj-abc123"},
)
print(tool["action"], tool["entitiesMasked"])

Methods

Method	API
`mask(text=, platform=)`	`POST /api/mask`
`emit_event(...)`	`POST /api/events`
`enforce_tool_call(...)`	`POST /api/mcp/enforce-tool-call`
`simulate_policy(...)`	`POST /api/policy/simulate`

Errors

Raises BleklineApiError with .status on HTTP failures.

See also: OpenAPI spec and TypeScript SDK.

Next steps: AI Enablement Stack · Quick start · Open workspace · Report issue