This record as markdown: /tools/io-github-aifity-omnigit-mcp/projects-write.md
What projects_write does on GitHub
AI agents use projects_write to create or update resources in GitHub, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitHub environment.
Why projects_write is rated Medium
This tool modifies GitHub Project data (likely cards, columns, or metadata) rather than reading, executing code, deleting, or moving money. Modification is reversible through subsequent updates. Severity is medium because unauthorized modification of project planning data could disrupt team workflows, but the impact is limited to project metadata rather than code or production systems.
From the tool's definition Tool name explicitly includes 'write' and description states 'Modify GitHub Project items' - a reversible operation that creates or changes data without deletion.
Attacks that exploit this kind of access
The rule that runs projects_write safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For projects_write, this is the rule to start with:
projects_write stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every projects_write call is checked against it from then on.
Questions about projects_write
Modify GitHub Project items. It is categorised as a Write tool in the GitHub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitHub MCP server in PolicyLayer and add a rule for projects_write: 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 GitHub. Nothing to install.
projects_write is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the projects_write 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 projects_write. 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.
projects_write is provided by the GitHub MCP server (oci:ghcr.io/aifity/omnigit-mcp:0.5.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue