cdp-bridge-mcp
Let one AI workspace operate multiple signed-in Chrome accounts. Route each MCP request to its own browser profile through a self-hosted bridge.
Runs with mockssource: GitHubPythonMITcommit cc33c4161f29
Python, MIT licensed. The project labels itself: browser automation, chrome extension, mcp server and model context protocol.
cdp-bridge-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
cdp-bridge installs cleanly, both stdio and streamable-http MCP transports start and respond correctly to initialize and tools/list, returning 12 browser automation tools ready for a Chrome extension connection.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 86 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
- Install time
- under a minute
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- Stdio mode: 'cdp-bridge --transport stdio' with initialize+tools/list returned server info and 12 tools. Streamable-http: POST /mcp returned 200 with SSE. browser_get_tabs returned '{"tabs":[],"active_tab":null}'
- Model tokens used
- 92,372
- Exact commit tested
- cc33c4161f29
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
tokens used
92,372
The project is a Python MCP (Model Context Protocol) server that bridges MCP clients to real browse…
**Install**: `uv sync` installed all 37 packages without errors. The project builds cleanly from so…
**What I verified**:
- `cdp-bridge --help` exits 0 with correct usage output
- `cdp-bridge-extension-path` prints the correct extension directory at `/work/repo/src/cdp_bridge/…
- MCP stdio mode: `initialize` returns server info `tmwebdriver-bridge v1.27.0`; `tools/list` retur…
- MCP streamable-http mode: POST `/mcp` returns `200` with proper SSE messages and session manageme…
- `browser_get_tabs` tool call returns `{"tabs": [], "active_tab": null}` (correct — no browser ext…
**No errors encountered** — everything worked on first install.
**Limitations**: The project has **no test suite** (confirmed by CLAUDE.md and file search). The to…Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 0.5 minutes, faster than the median of the 14 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Of the 15 browser-automation projects Argusic has installed and timed, cdp-bridge-mcp was the 1st fastest to reach a running state, and 13 of 15 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.08 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.07 |
Topics (from GitHub)
browser-automationchrome-extensionmcp-servermodel-context-protocol
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cdp-bridge-mcp)Questions
- Does cdp-bridge-mcp run?
- cdp-bridge-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test cdp-bridge-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit cc33c4161f29. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test cdp-bridge-mcp?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does cdp-bridge-mcp take to install?
- 0.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does cdp-bridge-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing cdp-bridge-mcp?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does cdp-bridge-mcp compare with the alternatives?
- Of the 15 browser-automation projects Argusic has installed and timed, cdp-bridge-mcp was the 1st fastest to reach a running state, and 13 of 15 reached one at all.
- Where is the evidence for cdp-bridge-mcp?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.