MCP, MCP server
Context Bridge Mcp
A lightweight, project-agnostic MCP server that gives Claude Code agents shared context across multiple repos on the same machine.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
INSTALL_LIFECYCLE_HOOK SECRETS_PATH_CREDENTIAL
Why this grade
- INSTALL_LIFECYCLE_HOOK Medium
A package install hook (preinstall, install, postinstall or prepare) runs a script.
package.json, line 36
prepare - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
README.md, line 839
The headless tests spawn `claude -p` and drive the bridge as a real agent would. They need a Claude account (subscription OAuth via `~/.claude/.credentials.json`, or a long-lived t
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
.claude/skills/skill-creator/eval-viewer/generate_review.py, line 291
result = subprocess.run(
.claude/skills/skill-creator/scripts/improve_description.py, line 35
result = subprocess.run(
.claude/skills/skill-creator/scripts/run_eval.py, line 85
process = subprocess.Popen(
Install and update
Concern
runs a script at install time.
INSTALL_LIFECYCLE_HOOK
package.json, line 36
prepare
Network
Concern
can reach a host that is not written as a fixed address.
NETWORK_NO_FIXED_HOST
.claude/skills/mcp-builder/reference/node_mcp_server.md, line 474
const response = await axios.get(`${API_URL}/resource/${resourceId}`);
.claude/skills/mcp-builder/reference/node_mcp_server.md, line 480
return axios.get(`${API_URL}/resource/${resourceId}`)
.claude/skills/mcp-builder/reference/python_mcp_server.md, line 260
response = requests.get(f"{API_URL}/resource/{resource_id}") # Blocks
Show more
.claude/skills/skill-creator/eval-viewer/viewer.html, line 666
const resp = await fetch("/api/feedback");
.claude/skills/skill-creator/eval-viewer/viewer.html, line 1012
fetch("/api/feedback", {
.claude/skills/skill-creator/eval-viewer/viewer.html, line 1044
fetch("/api/feedback", {
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL
README.md, line 839
The headless tests spawn `claude -p` and drive the bridge as a real agent would. They need a Claude account (subscription OAuth via `~/.claude/.credentials.json`, or a long-lived t
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Pass
No encoded or minified payload found.
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit a8ef1781bbd8. requests shell access. The manifest names this permission. runs a script at install time. can reach a host that is not written as a fixed address. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: a8ef1781bbd81b077c861a9ab778a395d7f14bbb
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.