Blumira MCP Server

An MCP server for the Blumira SIEM public API. It lets an AI agent review and work Blumira findings (detections), look up Blumira Agent devices and keys, and, for MSPs, do the same across all sub-accounts.

• Transport: MCP Streamable HTTP at POST /mcp, health probe at GET /health

• Stateless and multi-tenant: credentials arrive on every request as HTTP headers and are never stored; an OAuth access token is obtained per request and not cached

• Every tool is listed from the first tools/list

• Python 3.12, uv, FastMCP, httpx

• License: Apache-2.0, Copyright 2026 MSPbots.ai

MSPbots Connector

The MCP Gateway built for MSPs: visible, controlled, and your data stays where it belongs.

Get started at connect.mspbots.ai →

MSPbots Connector gives your AI clients one MCP URL to reach your entire MSP stack (RMM, PSA, documentation, security, finance), and gives you control over who can call which tool and a record of everything that was called.

Hosted service: connect.mspbots.ai · Free to use.

Why Connector

Quick start

1. Sign up at connect.mspbots.ai.

2. Connect your vendors. Pick from 150+ connectors and authorize each one on the vendor's own page, or bring your own API keys. No extra vendor accounts needed.

3. Set access. Create roles and decide which tools each role may call. Nothing is allowed until you allow it.

4. Add your MCP URL to your AI client. Copy the URL from your Connector dashboard into Claude, ChatGPT, Cursor, VS Code, Gemini, Codex, or any MCP-capable client.

5. Ask your AI to do real work, and watch every call appear in the audit log.

Features

Unified gateway

• One MCP URL for all your AI clients

• 150+ connectors across the MSP stack

• Custom MCP servers supported, free

• Authorization happens on each vendor's own page; the AI never sees passwords or tokens

• Bring your own credentials: use the vendor API keys you already have

• Multiple accounts per app; connect once, reuse across AI clients

• Tool search: finds the right action for the task

• One sign-in; vendor credentials are injected behind the scenes and OAuth tokens refresh automatically

Visibility

• Audit log for every tool call (who, which vendor, when)

• Usage dashboard: call volume, top vendors, error rate, per-user activity

• Export audit logs to CSV, or stream to Loki, Graylog, or LogScale (SIEM)

• Optional recording of tool arguments and result summaries (off by default, enabled per organization)

Control

• Per-role, per-tool allowlist, deny by default

• owner / admin / member roles

• SCIM provisioning with Entra ID, Okta, JumpCloud, and Google Workspace

Security

• Credentials encrypted one record at a time (AES-256-GCM, per-record key)

• AI clients authenticate with OAuth 2.1 + PKCE

• Vendor responses are scanned for prompt-injection patterns and returned as structured data. This is one layer of defense, not a guarantee against every attack.

• Static egress IP for customer firewall and API allowlisting

Pricing

Free.

Links: connect.mspbots.ai · mspbots.ai

Related MCP server: HUMAN Security MCP Server

Authentication headers

Send either the client id and secret or a JWT token.

Where to get them:

• Create API credentials in the Blumira app's API access settings (organization keys work on the organization; MSP keys also work on every sub-account).

• With a client id and secret the server requests a token from https://auth.blumira.com/oauth/token (client credentials, audience https://api.blumira.com/public-api/v1) on each request. If a JWT token is sent, it is used directly and takes precedence.

A request to /mcp with neither credential set gets HTTP 401 describing both options.

Tools

All tools return a JSON string. List tools take page (from 1) and page_size (default 50, max 200), and return {items, count, page, total_pages, total_items, has_more}. They also take offset (record position from 0, overrides page) and return offset / next_offset: when a page is cut to fit the response size limit, the rest of it is on no other page, so continue with next_offset, which starts right after the last record returned.

Organization:

MSP (sub-accounts):

Errors come back as a JSON envelope instead of an exception:

{"error": {"code": "unauthorized", "message": "Blumira rejected the client id / secret (token request failed)", "retryable": false}}

code is one of not_configured, unauthorized, not_found, invalid_argument, rate_limited, upstream_error.

Run locally

uv sync
uv run python -m blumira_mcp          # listens on 0.0.0.0:8080

or with Docker:

docker build --platform linux/amd64 -t blumira-mcp:dev .
docker run --rm -p 8080:8080 blumira-mcp:dev

Configuration (environment variables, all optional): MCP_HTTP_HOST (default 0.0.0.0), MCP_HTTP_PORT (default 8080), LOG_LEVEL (default INFO). Credentials are never read from the environment.

Testing example

# list tools
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Blumira-Client-Id: your-client-id" \
  -H "X-Blumira-Client-Secret: your-client-secret" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

# highest-priority findings
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Blumira-Client-Id: your-client-id" \
  -H "X-Blumira-Client-Secret: your-client-secret" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"blumira_findings_list","arguments":{"priority":1,"page_size":10}}}'

Unit tests (no network access needed):

uv run pytest

Delivery notes

• All tools always listed. Older versions only listed navigation tools until one was called, which hid the other tools behind a stateless gateway. All 30 tools are now listed up front; blumira_navigate and blumira_back remain and only describe the tools.

• Tool count (30). Kept as is because the tool names and argument names (including name.contains and name.regex) are an existing contract.

• Write tools. Resolve, assign and comment tools change findings; they are annotated readOnlyHint=false and their descriptions tell the agent to act only on an explicit request. There are no delete tools.

License

Apache License 2.0 - see LICENSE and NOTICE.