Skills/PyPI/orchestra-mcp

orchestra-mcp@0.1.9

VERIFIED· install only

Publisher claims: "MCP server testing and orchestration tool" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ahaan-chaudhuri · publishing for 267 daysInstalls 212Last detonated 9 h ago
$claude mcp add orchestra-mcp -- uvx orchestra-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
API_KEYORCHESTRA_API_TOKENORCHESTRA_OAUTH_CLIENT_IDORCHESTRA_OAUTH_CLIENT_SECRETORCHESTRA_OAUTH_PROVIDERTOKENConfiguration, not credentials: KEY, MCP_URL, NAME, ORCHESTRA_ALLOWED_ORIGINS, ORCHESTRA_WORKSPACE, PASS, STAGING_KEY, TEAM
Where it talks to
no vendor host named in the codeAlso exa.ai, adaly.ai, ahaan.world, deepwiki.com, jsonrpc.org — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names exa.ai, adaly.ai, ahaan.world, deepwiki.com, jsonrpc.org as well as its own vendor. The guard injects API_KEY, ORCHESTRA_API_TOKEN, ORCHESTRA_OAUTH_CLIENT_ID, ORCHESTRA_OAUTH_CLIENT_SECRET, ORCHESTRA_OAUTH_PROVIDER, TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx orchestra-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageorchestra/server/models.py:83 · npx invocation of non-well-known package — may execute untrusted code# a reference to anything: a caller holding `npx -y @scope/pkg` has theFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageorchestra/vendor_target.py:88 · npx invocation of non-well-known package — may execute untrusted codereference server runs through npx or uvx. Such a package is not "local" inFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageorchestra/cli_init.py:757 · npx invocation of non-well-known package — may execute untrusted code'command for a published package, e.g. "npx -y @scope/server-x" or 'Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageorchestra/mcp_server.py:291 · npx invocation of non-well-known package — may execute untrusted code"being watched, a hosted URL or a launch command like 'npx -y "Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedorchestra/discovery.py:73 · Python subprocess execution detectedcompleted = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packageorchestra/schema_parsing/registry.py:15 · npx invocation of non-well-known package — may execute untrusted codecommand: npxFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionorchestra/scaffold.py:349 · File type combined with upload action — agent may exfiltrate local data files#: Where the run writes junit.xml and summary.json, and what gets uploaded.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageorchestra/scaffold.py:412 · npx invocation of non-well-known package — may execute untrusted code# ubuntu-latest ships Node and npm (so an `npx -y <server>` stdioFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedorchestra/cli_watch.py:152 · Python subprocess execution detectedresult = subprocess.run(build, shell=True, cwd=path, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packageorchestra/scaffold.py:365 · npx invocation of non-well-known package — may execute untrusted code`npx -y <package>` workflow tests the last release rather than the PR,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)orchestra/engine/record.py:11 · MCP server using network transport (SSE/HTTP) — data sent over networkits own seam: mcp_server passes its module's call_tool_once (which its testsFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈47 tok
1 file · 72 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for orchestra-mcp@0.1.9 as of 9 h ago. This is the package itself, not its dependencies.