Skills/PyPI/odoo-safe-mcp

odoo-safe-mcp@3.0.0

VERIFIED· not started

Publisher claims: "AI firewall and MCP server for Odoo 14-20: safe reads, guarded drafts and signed human approvals without sending your Odoo credentials to the cloud." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher makelele29 · publishing for 26 daysInstalls 278Last detonated 23 h ago
$claude mcp add odoo-safe-mcp -- uvx odoo-safe-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
ODOO_API_KEYODOO_PASSWORDConfiguration, not credentials: ODOO_APPROVAL_WAIT_SECONDS, ODOO_DB, ODOO_DRY_RUN, ODOO_GUARD_PROXY_URL, ODOO_GUARD_PUBLIC_KEYS, ODOO_GUARD_URL, ODOO_SAFE_GUARD_KEY, ODOO_SAFE_STATE_DIR, ODOO_TIMEOUT, ODOO_URL, ODOO_USERNAME
Where it talks to
odoosafemcp.stream (its own)Also odoo.com — 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
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names odoo.com as well as its own vendor. The guard injects ODOO_API_KEY, ODOO_PASSWORD only into requests to odoosafemcp.stream (and its subdomains) and refuses the rest.

$vet-skills run --secrets ODOO_API_KEY=odoosafemcp.stream,ODOO_PASSWORD=odoosafemcp.stream -- uvx odoo-safe-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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
URL with suspicious TLDodoo_safe_mcp/guard.py:35 · URL with suspicious TLD — commonly used for phishing/malware401: "Pro Guard licence missing or invalid. Check ODOO_SAFE_GUARD_KEY or get one at https://odoosafemcp.stream/#pricing.",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_zero_credential.py:156 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files@pytest.mark.parametrize("bad_id", ["../../etc/passwd", "not-a-uuid", "", "12345678-1234-1234-1234-1234567890ab/../x"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with suspicious TLDpyproject.toml:50 · URL with suspicious TLD — commonly used for phishing/malwareHomepage = "https://odoosafemcp.stream"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDpyproject.toml:54 · URL with suspicious TLD — commonly used for phishing/malware"Get Pro API Key" = "https://odoosafemcp.stream/#pricing"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsodoo_safe_mcp/config.py:1 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Configuration loaded from environment variables (set in the MCP client config or a .env file)."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL with suspicious TLDtests/test_cli_and_config.py:40 · URL with suspicious TLD — commonly used for phishing/malwareassert _guard_base_url(raw) == "https://odoosafemcp.stream"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDpyproject.toml:51 · URL with suspicious TLD — commonly used for phishing/malwareDocumentation = "https://odoosafemcp.stream/#how"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDtests/test_cli_and_config.py:37 · URL with suspicious TLD — commonly used for phishing/malware["https://odoosafemcp.stream/v1/guard", "https://odoosafemcp.stream/", "https://odoosafemcp.stream/v2", ""],Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDodoo_safe_mcp/config.py:11 · URL with suspicious TLD — commonly used for phishing/malwareDEFAULT_GUARD_URL = "https://odoosafemcp.stream"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with suspicious TLDodoo_safe_mcp/rules.py:180 · URL with suspicious TLD — commonly used for phishing/malwareUPGRADE_URL = "https://odoosafemcp.stream/#pricing"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈74 tok
1 file · 31 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for odoo-safe-mcp@3.0.0 as of 23 h ago. This is the package itself, not its dependencies.