bagelBLOCK
Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Bits to atoms.Atoms to bits.
If you still have a script called parsebagfinal_v7.py, we need to talk.
Bagel by Extelligence lets you ask questions about robotics, drone, and IoT data in plain English. Every calculation over your message data is DuckDB SQL, not model guesswork, and Bagel shows you the query so you can audit it.
Is my IMU sensor overheating?
Bagel also has an intelligent edge data reduction pipeline: describe an event and Bagel runs the detection on the robot, keeping the windows that matter and dropping the rest. An MCP server puts all of it in your LLM's hands: Claude Code, Gemini, Cursor, or a fully local model.
Bagel was the first MCP server to ship a real
80ffcf9ae82dOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add ros2-kilted:2.4.3 -- docker run -i --rm ghcr.io/extelligence-ai/bagel/ros2-kilted:2.4.3:None
Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ping | read | Reply with pong. |
Trust audit
BLOCKgrade F · trust 59/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- declared (6 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (25)
.env
self._struct = pickle.load(f) # noqa: S301
.dockerignore
importlib.import_module(f"{BaseModule.SOURCE_FACTORY.value}.{ds_type.value}")importlib.import_module(import_path).register()
module: Module = importlib.import_module(import_path)
importlib.import_module(config["module"]).register()
discovered = importlib.import_module(module_name)
`http://127.0.0.1:${port}/sse`, '--transport', 'sse-only', '--allow-http'];BAGEL_POSTGRES_TEST_URL: postgres://postgres:bagel-ci-test@localhost:5432/postgres
text = "IO Error: could not connect using 'postgresql://alice:s3cr3t@host/db'"
"postgresql://alice:[email protected]:5432/prod: name resolution failed"
BAGEL_POSTGRES_TEST_URL=postgres://postgres:bagel@localhost:5433/postgres \
imu_probe.mcap
sample.bag
part_0.db3
part_1.db3
part_2.db3
.env
.pre-commit-config.yaml
digest = hashlib.md5(usedforsecurity=False)
digest = hashlib.md5(usedforsecurity=False)
# exfiltration path via ambient env vars the runner injects into
`Uvicorn running on http://0.0.0.0:8000`.
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
Gates applied: no_behavioural_pass.
80ffcf9ae82dfull audit observations/trust-audit/mcp-server/extelligence-ai__bagel.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 80ffcf9ae82d | BLOCK | F | 59 | first audit |
Questions
What is the bagel MCP server?
Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.
What tools does bagel expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is bagel safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (59/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does bagel need?
It reads SMITHERY_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does bagel run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as bagel.
How current is this page?
The grade is for one exact copy of the source (80ffcf9ae82d), read on 2026-10-07. The repository is watched and re-audited when it changes.