post_bluesky
⚠ POSTS PUBLICLY & IRREVERSIBLY: post to Bluesky via YOUR handle + app-password (BYOK; create at Settings→App Passwords, NOT your login). Max 300 chars. dry_run to preview.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/post-bluesky.md
What post_bluesky does on Gateway
AI agents use post_bluesky to create or update resources in Gateway, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gateway environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | the post text (max 300) |
handle | string | — | your WingMan handle (rate limiting) |
dry_run | boolean | — | preview, don't post |
bsky_handle | string | Yes | your Bluesky handle, e.g. you.bsky.social |
app_password | string | Yes | an app password (not your account password) |
Parameters from the server's own tool schema.
Why post_bluesky is rated Medium
The tool publishes a public post to Bluesky. While the description says 'irreversibly,' posts on social platforms can typically be deleted, making this closer to Write than Destructive. However, the public nature and reputational impact of a misused post (e.g., spam, harmful content posted under a real user's handle) justify high severity.
From the tool's definition ⚠ POSTS PUBLICLY & IRREVERSIBLY: post to Bluesky via YOUR handle + app-password
Attacks that exploit this kind of access
The rule that runs post_bluesky safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For post_bluesky, this is the rule to start with:
post_bluesky 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 Gateway, apply this rule, and every post_bluesky call is checked against it from then on.
Questions about post_bluesky
⚠ POSTS PUBLICLY & IRREVERSIBLY: post to Bluesky via YOUR handle + app-password (BYOK; create at Settings→App Passwords, NOT your login). Max 300 chars. dry_run to preview. It is categorised as a Write tool in the Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
post_bluesky accepts 5 parameters: text, handle, dry_run, bsky_handle, app_password. Required: text, bsky_handle, app_password. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for post_bluesky: 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 Gateway. Nothing to install.
post_bluesky 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 post_bluesky 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 post_bluesky. 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.
post_bluesky is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue