orchestrator-mcp-server
PyPI
v0.6.1
Published by crak1644 — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Capability-routed MCP server: route work to the LLM that is best at it.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Hardcoded GitHub token in test/example/packaging MTC-SRC-008 | exfiltration |
2. Client adoption risk — 99 − 7 = 92. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
In the server's implementation (`smoke_workflow_live.py:135`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: str) -> str: done = subprocess.run(["git", *args], cwd=repo, capture_output=True, text=True) if done.returncode
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server smoke_workflow_live.py
A hardcoded GitHub token (a live-looking credential hardcoded in shipped code) appears in `tests/test_review_secrets.py:28`. Verify whether this is a real credential; if so, remove and rotate it.
Evidence: GitHub token: ghp_…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_review_secrets.py
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/fixtures/fake_cli.py:50`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: N) grandchild = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(300)"]) with open(sys.a
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/fixtures/fake_cli.py
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_cli_entrypoint.py:89`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: r(tmp_path) done = subprocess.run( [sys.executable, "-m", "orchestrator_mcp.server"], cwd=tmp_path,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_cli_entrypoint.py
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_code_execution.py:103`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: first"], ): subprocess.run(["git", *args], cwd=path, check=True, capture_output=True) return path @pyt
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_code_execution.py
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_consult_store.py:335`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: art_at)] openers = [subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_consult_store.py
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_workflow_service.py:211`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ", "t"], ): subprocess.run(command, cwd=path, check=True) (path / "src").mkdir() (path / "src" / "a.
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_workflow_service.py
Each tool and what it can reach — statically extracted from the published source.
orchestrator_apply_fixesno sensitive capabilityorchestrator_cancel_reviewno sensitive capabilityorchestrator_delete_all_consultationsno sensitive capabilityorchestrator_delete_all_reviewsno sensitive capabilityorchestrator_delete_all_workflowsno sensitive capabilityorchestrator_delete_consultationno sensitive capabilityorchestrator_delete_reviewno sensitive capabilityorchestrator_delete_workflowno sensitive capabilityorchestrator_finalize_reviewno sensitive capabilityorchestrator_get_consultationno sensitive capabilityorchestrator_get_reviewno sensitive capabilityorchestrator_list_consult_agentsno sensitive capabilityorchestrator_list_reviewsno sensitive capabilityorchestrator_record_fix_roundno sensitive capabilityorchestrator_request_delete_allno sensitive capabilityorchestrator_request_delete_all_consultationsno sensitive capabilityorchestrator_request_delete_all_workflowsno sensitive capabilityorchestrator_retry_reviewno sensitive capabilityorchestrator_reviewno sensitive capabilityorchestrator_review_runno sensitive capabilityorchestrator_test_reviewersno sensitive capabilityorchestrator_workflow_cancelno sensitive capabilityorchestrator_workflow_plan_replanno sensitive capabilityorchestrator_workflow_plan_stepno sensitive capabilityorchestrator_workflow_record_host_stepno sensitive capabilityorchestrator_workflow_replanno sensitive capabilityorchestrator_workflow_run_stepno sensitive capabilityorchestrator_workflow_startno sensitive capabilityorchestrator_workflow_statusno sensitive capabilityScan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.6.1 latest |
A 92/100 | 7 | 1.13.0 | 2026-08-27 |
v0.5.6 |
A 92/100 | 6 | 1.13.0 | 2026-08-25 |
v0.5.4 |
A 92/100 | 6 | 1.12.1 | 2026-08-24 |
v0.5.1 |
A 92/100 | 6 | 1.12.1 | 2026-08-16 |
v0.5.0 |
A 92/100 | 6 | 1.12.1 | 2026-08-14 |
v0.4.2 |
A 98/100 | 3 | 1.12.1 | 2026-08-09 |
v0.3.0 |
A 99/100 | 2 | 1.12.1 | 2026-08-05 |
v0.2.0 |
A 99/100 | 2 | 1.12.1 | 2026-08-04 |
v0.1.2 |
A 99/100 | 0 | 1.12.1 | 2026-08-03 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan orchestrator-mcp-server --online --registry pypi
Independent packages implementing the same tool, scanned with the same engine. Compare all 5 side by side →
Perssona Orchestrator MCP — control canvas, terminals and workflows from Claude Code and Codex
Orchestrates multiple MCP servers with unified tool search (BM25/regex) and deferred loading
Serveur MCP pour l'orchestration de tâches distantes (SSH/SFTP) avec une file d'attente persistante.
MCP Orchestrator - Discover and install MCPs with automatic OAuth support. Uses Claude CLI for OAuth MCPs (Canva, Asana, etc). 34 trusted MCPs from Claude Partners.
Free public tax reference data — GST/VAT, income, company and capital-gains tax rules for 50+ countries.
The approval gate for unattended UCP buying agents — a policy/approval MCP proxy in front of a merchant's UCP checkout endpoint.
Autotask PSA MCP server. Generic entity query/get/create/update across the full REST API plus convenience tools for tickets, companies, contacts, projects, tasks and time entries. AI-safe with readonly mode and destructive-action confirmation. stdio + opt
MCP server for B2C Commerce developer experience tools
Search, compare and contact real-world companies through a public MCP business directory.
Norwegian business register (Brønnøysundregistrene) as an MCP server — companies, roles, subunits and annual accounts, with the register's silent traps encoded as guards.