Call GitHub REST API directly. Uses the GitHub token from local_profile.json.
AI agents invoke github_api to trigger actions in Odoo Claude MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool makes arbitrary GitHub REST API calls, which can span reading repos, writing/creating content, triggering workflows, managing webhooks, or even deleting repositories depending on the endpoint called. Since the tool allows arbitrary API calls with no described restriction, the most severe applicable category is Execute (with potential for Destructive actions).
From the tool's definition Call GitHub REST API directly
Documented attack patterns abuse exactly the kind of access github_api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Odoo Claude MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for github_api:
{
"version": "1",
"default": "deny",
"tools": {
"github_api": {
"limits": [
{
"counter": "github_api_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} github_api stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Call GitHub REST API directly. Uses the GitHub token from local_profile.json. It is categorised as a Execute tool in the Odoo Claude MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Odoo Claude MCP server in PolicyLayer and add a rule for github_api: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Odoo Claude MCP. Nothing to install.
github_api is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the github_api rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for github_api. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
github_api is provided by the Odoo Claude MCP server (rosenvladimirov/odoo-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Odoo Claude MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
180 Odoo Claude MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.