Palinode MCP Server
palinode
PyPI
v0.17.0
Published by phasespace-labs — 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.
The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. 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.
Findings 12
high Shell/command execution in server code (palinode/api/routers/health.py)MTC-SRC-002
In the server's implementation (`palinode/api/routers/health.py:72`): 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: try: unpushed = subprocess.run( ["git", "rev-list", "--count", "origin/main..HEAD"], cwd
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 palinode/api/routers/health.py
high Shell/command execution in server code (palinode/cli/__init__.py)MTC-SRC-002
In the server's implementation (`palinode/cli/__init__.py:215`): 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: try: subprocess.run(["sudo", "systemctl", "stop", svc], check=True) console.print(f"[gree
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 palinode/cli/__init__.py
high Shell/command execution in server code (palinode/cli/mcp_smoke.py)MTC-SRC-002
In the server's implementation (`palinode/cli/mcp_smoke.py:114`): 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: top" proc = subprocess.run( # nosec B603,B607 - argv form, no shell ["pgrep", "-f", pattern
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 palinode/cli/mcp_smoke.py
high Shell/command execution in server code (palinode/cli/worktree.py)MTC-SRC-002
In the server's implementation (`palinode/cli/worktree.py:36`): 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: etedProcess: return subprocess.run( # nosec B603,B607 - argv form, no shell ["git", *args], cwd=cwd
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 palinode/cli/worktree.py
high Shell/command execution in server code (palinode/core/git_tools.py)MTC-SRC-002
In the server's implementation (`palinode/core/git_tools.py:62`): 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: deliberately — never ``shell=True``, never string-interpolated commands — so user-supplied inputs (file paths, comm
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 palinode/core/git_tools.py
high Shell/command execution in server code (palinode/diagnostics/checks/git_identity.py)MTC-SRC-002
In the server's implementation (`palinode/diagnostics/checks/git_identity.py:29`): 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: etedProcess: return subprocess.run( ["git", "-C", cwd, *args], capture_output=True, text=Tru
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 palinode/diagnostics/checks/git_identity.py
high Shell/command execution in server code (palinode/diagnostics/checks/git_remote.py)MTC-SRC-002
In the server's implementation (`palinode/diagnostics/checks/git_remote.py:29`): 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: etedProcess: return subprocess.run( ["git", "-C", cwd, *args], capture_output=True, text=Tru
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 palinode/diagnostics/checks/git_remote.py
high Shell/command execution in server code (palinode/diagnostics/checks/watcher.py)MTC-SRC-002
In the server's implementation (`palinode/diagnostics/checks/watcher.py:52`): 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: try: result = subprocess.run( ["ps", "-ef"], capture_output=True, text=Tru
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 palinode/diagnostics/checks/watcher.py
high Shell/command execution in server code (palinode/ingest/pipeline.py)MTC-SRC-002
In the server's implementation (`palinode/ingest/pipeline.py:128`): 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: result = subprocess.run( ["pdftotext", filepath, "-"], capture_output=Tru
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 palinode/ingest/pipeline.py
medium Unconstrained URL/host parameter "url" on "palinode_ingest"MTC-CAP-007
Tool "palinode_ingest" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool palinode_ingest · inputSchema.properties.url
low Shell/command execution in packaging/dev tooling (tests/test_api_bearer_auth.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_api_bearer_auth.py:56`): 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: pop(k, None) return subprocess.run( [sys.executable, "-c", "from palinode.api.server import app # noqa: F40
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_api_bearer_auth.py
low Dynamic module load from a non-literal in packaging/dev tooling (tests/test_bench_perf.py)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_bench_perf.py:86`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: s_deferred( __import__( "palinode.core.ollama_client", fromlist=["get_ollama_client"]
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_bench_perf.py
Tools 32
Each tool and what it can reach — statically extracted from the published source.
palinode_ingestingests untrusted inputpalinode_archiveno sensitive capabilitypalinode_archive_expiredno sensitive capabilitypalinode_blameno sensitive capabilitypalinode_cluster_neighborsno sensitive capabilitypalinode_consolidateno sensitive capabilitypalinode_dedup_suggestno sensitive capabilitypalinode_dependsno sensitive capabilitypalinode_diffno sensitive capabilitypalinode_doctorno sensitive capability
Show 22 more tools ↓
palinode_doctor_deepno sensitive capabilitypalinode_entitiesno sensitive capabilitypalinode_forget_withdrawno sensitive capabilitypalinode_historyno sensitive capabilitypalinode_lintno sensitive capabilitypalinode_listno sensitive capabilitypalinode_orphan_repairno sensitive capabilitypalinode_promptno sensitive capabilitypalinode_pushno sensitive capabilitypalinode_readno sensitive capabilitypalinode_restoreno sensitive capabilitypalinode_reviewno sensitive capabilitypalinode_rollbackno sensitive capabilitypalinode_saveno sensitive capabilitypalinode_searchno sensitive capabilitypalinode_session_endno sensitive capabilitypalinode_session_initno sensitive capabilitypalinode_statusno sensitive capabilitypalinode_topic_coverageno sensitive capabilitypalinode_traceno sensitive capabilitypalinode_triggerno sensitive capabilitypalinode_unretractno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (32 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 10
Scan 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 |
|---|---|---|---|---|
v0.17.0 latest |
A 93/100 | 12 | 1.13.0 | 2026-09-08 |
v0.16.0 |
A 93/100 | 12 | 1.13.0 | 2026-09-06 |
v0.15.0 |
A 93/100 | 11 | 1.13.0 | 2026-09-04 |
v0.14.0 |
A 93/100 | 11 | 1.13.0 | 2026-08-27 |
v0.13.0 |
A 93/100 | 11 | 1.13.0 | 2026-08-25 |
Show 5 more versions ↓
v0.12.0 |
A 93/100 | 11 | 1.12.1 | 2026-08-12 |
v0.11.0 |
A 93/100 | 11 | 1.12.1 | 2026-08-09 |
v0.10.1 |
A 93/100 | 11 | 1.12.1 | 2026-08-06 |
v0.10.0 |
A 93/100 | 11 | 1.12.1 | 2026-08-03 |
v0.9.8 |
A 93/100 | 11 | 1.12.1 | 2026-08-02 |
Embed this score
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.
Verify this score yourself
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 palinode --online --registry pypiMore in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.