Integrations

Use Saywise from your AI tools

Saywise runs an MCP server, so the agent you already work in can build out your profile, post your AI work, and find jobs that match you. Stories and Q&A answers land as private drafts you review before anything goes public; profile edits happen only with your approval in the conversation.

Claude Code (CLI)

Install the Saywise plugin — the MCP server plus story-drafting skills and hooks:

claude plugin marketplace add saywise/skills
claude plugin install saywise-skills@saywise

New to plugins? See Claude’s plugin docs.

Claude Desktop and claude.ai (desktop and web app)

Open Settings → Connectors → Add custom connector.
Paste the server URL:
```
https://saywise.com/api/mcp/v1
```
Sign in when prompted.

Once connected, the Saywise tools are there whenever you ask.

Other agents

Any client that speaks MCP over Streamable HTTP can connect — point it at the URL above. Auth is standard OAuth 2.1 with dynamic client registration, so there are no API keys to manage; the client opens a browser for consent on first use.

What the tools do

saywise_create_suggested_drafts— your agent sends the session’s content and Saywise generates story drafts for your profile.
saywise_get_story_scan_instructions — guides your agent through mining past conversations for work worth telling.
saywise_get_usage_stats_instructions and saywise_submit_usage_stats — measure your AI usage locally and, once you approve the exact numbers, add them to your AI Fluency section.
saywise_get_profile and the saywise_edit_* tools — your agent reads your profile and, with your approval on each change, edits every section: bio and links, work history, education, projects, credentials, skills, and your AI Fluency section.
saywise_suggest_qa_answers— your agent interviews you and drafts Q&A answers as private suggestions you accept on your profile.
saywise_get_job_matches, saywise_get_job_fit and saywise_search_jobs — see your scored matches, how you fit one job and what would close the gaps, and search everything published.

Start with a prompt

Connected? Paste one of these into your agent:

Fetch my Saywise profile and review it with me section by section — what's missing, what's weak. Make the edits we agree on, then refresh my job matches and walk me through the top ones.

Turn my past conversations into Saywise post drafts. Show me up to 5 recent sessions where something real shipped, got fixed, or got measured, and present them as options. Send the picks to Saywise with its tools and give me the review link. Skip anything sensitive.

Privacy

Conversation scans run on your machine or in your account — only the content of sessions you pick is sent to Saywise, so it can generate the drafts.
Drafts stay private until you approve them yourself.
Usage stats are aggregate numbers only — counts, dates, model names — and are submitted only after your agent shows you the exact payload and you say yes.

Claude Code (CLI)

Install the Saywise plugin — the MCP server plus story-drafting skills and hooks:

claude plugin marketplace add saywise/skills
claude plugin install saywise-skills@saywise

What the tools do

saywise_create_suggested_drafts— your agent sends the session’s content and Saywise generates story drafts for your profile.

saywise_get_story_scan_instructions — guides your agent through mining past conversations for work worth telling.

saywise_get_usage_stats_instructions and saywise_submit_usage_stats — measure your AI usage locally and, once you approve the exact numbers, add them to your AI Fluency section.

saywise_get_profile and the saywise_edit_* tools — your agent reads your profile and, with your approval on each change, edits every section: bio and links, work history, education, projects, credentials, skills, and your AI Fluency section.

saywise_suggest_qa_answers— your agent interviews you and drafts Q&A answers as private suggestions you accept on your profile.

saywise_get_job_matches, saywise_get_job_fit and saywise_search_jobs — see your scored matches, how you fit one job and what would close the gaps, and search everything published.

Start with a prompt

Connected? Paste one of these into your agent:

Fetch my Saywise profile and review it with me section by section — what's missing, what's weak. Make the edits we agree on, then refresh my job matches and walk me through the top ones.

Turn my past conversations into Saywise post drafts. Show me up to 5 recent sessions where something real shipped, got fixed, or got measured, and present them as options. Send the picks to Saywise with its tools and give me the review link. Skip anything sensitive.

Privacy

Conversation scans run on your machine or in your account — only the content of sessions you pick is sent to Saywise, so it can generate the drafts.

Drafts stay private until you approve them yourself.

Usage stats are aggregate numbers only — counts, dates, model names — and are submitted only after your agent shows you the exact payload and you say yes.