AI Agent Connector

Connect an AI agent to the hosted Model Context Protocol server today so it can capture, annotate, verify, and share screenshots with you or another agent.

Packaged agent plugins

The Codex, Claude Code, and Gemini CLI packages are prepared for the public-source release. Their Git-backed install commands will become available when the repository opens. Google Antigravity and any compatible client can use the manual MCP connector below today.

Codex

codex plugin marketplace add mohalmah/Snipish && codex plugin add snipish@snipish-community

Claude Code

claude plugin marketplace add mohalmah/Snipish --sparse .claude-plugin plugins && claude plugin install snipish@snipish-community

Gemini CLI

gemini extensions install mohalmah/Snipish

Once public, each package will load the MCP connection and screenshot workflow guidance together. The guidance selects the lowest-token upload path, distinguishes editable and flattened annotations, verifies the result, and publishes only when asked.

Manual connector URL

https://snipish.mfdi.me/mcp

Connect through MCP today

Open your agent's MCP or connector settings.
Add a custom connector and enter the connector URL above.
Select Connect and sign in to Snipish.
Review the requested permissions and select Allow access.

Compatible clients register themselves automatically. Snipish uses OAuth 2.0 authorization code flow with PKCE and rotates refresh tokens, so no API key needs to be pasted into the agent.

Give the agent one prompt

Run the built-in snipish-agent-setup MCP prompt once. It gives the agent the ingest decision tree, annotation rules, verification step, and publish-only-when-asked guardrail.

Choose the lowest-token ingest path

Public web page	`snipish_capture_url`
Public or presigned image URL	`snipish_import_screenshot_url`
Local or private image file	`snipish_create_screenshot_upload` then raw HTTP PUT
Client cannot perform HTTP PUT	`snipish_upload_screenshot` base64 fallback

Binary upload URLs expire after ten minutes and work once. Their JSON response contains the preview resource URI, collection item ID, annotation revision, and the exact next action.

Choose how the agent annotates

Editable layers	Upload the clean image with `annotationState: "unannotated"`, inspect it, then add normalized rectangles, arrows, and text through MCP.
Already annotated	Let the agent draw with its own image tool, verify the result, then upload it with `annotationState: "flattened"`. Snipish will not tell the agent to recreate the same marks.

Snipish stores this state with the screenshot so later agents know whether markup is baked into the pixels. The annotate-screenshot MCP prompt teaches both modes, including contrast, label placement, coordinate conversion, and visual verification.

Agent workflows

Capture a public URL into the reusable AI Captures collection.
Import image URLs or upload raw binary files without putting base64 in the MCP call.
Read model-sized previews, originals, collection manifests, and annotation state.
Add editable layers, or upload locally drawn markup as a verified flattened image.
Publish a finished collection and return its clean share URL only when the user asks.

Annotation writes use a revision number. An agent must read the latest item before changing it, which prevents silent overwrites when a person and agent edit at the same time.

Permissions

`media:read`	View screenshots and their metadata
`media:write`	Upload screenshots to your workspace
`capture:create`	Capture public web pages for storage in Snipish
`collections:write`	Create collections and place screenshots
`collections:publish`	Publish collections for public sharing
`annotations:write`	Add, update, and delete annotations

Bearer-token fallback

For an MCP client without OAuth, create an API key under Dashboard, Settings, Integrations and send it as Authorization: Bearer snp_.... Treat that key as a secret; current API keys grant the complete MCP permission set.