Saya
Provides access to workspace context including Slack-visible channels, team memory, decisions, skills, and readiness state.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Sayawhat's the team's context on the onboarding process?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Install
Any MCP client (.mcp.json)
Point your client at Saya's central remote MCP endpoint. This JSON fallback is the safest path while remote MCP auth support varies by client.
{
"mcpServers": {
"saya": {
"url": "https://saya-mcp.luke-nittmann.workers.dev/mcp",
"transport": "streamable-http"
}
}
}Any agent (npx skills)
Installs the secondary usage-guide skill for skill-aware agents. The MCP endpoint remains the main product surface.
npx skills add creative-int/saya-pluginsClaude Code
Add the marketplace, then install the Saya plugin.
/plugin marketplace add creative-int/saya-plugins
/plugin install saya@sayaCodex
Add this repo as a Codex plugin marketplace, then install from /plugins.
codex plugin marketplace add creative-int/saya-pluginsCursor
Install Saya from the Cursor plugin marketplace.
Cursor -> Settings -> Plugins -> Add marketplace -> creative-int/saya-pluginsTo preview the available skills without installing:
npx skills add creative-int/saya-plugins --listRelated MCP server: TeamMCP
MCP surface
Saya exposes one central Streamable HTTP MCP server. Team identity and access come from per-team OAuth bearer auth plus workspace membership; never put tokens in repo files.
Tool | Scope | Purpose |
|
| Read bounded workspace context across team memory, Slack-visible channels, decisions, skills, and readiness state. |
|
| Run one curated, idempotent, approval-first action through Saya. |
|
| Check endpoint readiness, tool availability, adapter status, and next setup steps. |
Status / readiness
The deployed endpoint is repo-local v1. OAuth/resource metadata and the three
MCP tools are live, but the live Convex-backed team-brain adapter is not wired
yet; saya_context currently returns deterministic placeholder data. The
custom domain https://mcp.saya.computer/mcp is also not routed yet, so this
repo intentionally points at the current workers.dev origin.
Included skill
saya-team-brain— secondary usage guidance for agents deciding when to query Saya through MCP before answering. Useful for team memory, decision history, workspace norms, channel context, and "what does this team already know?" questions. Also answers toask-teamandteam-context.
The skill lives at
skills/saya-team-brain/SKILL.md.
Develop
pnpm install
pnpm generate # regenerate all adapters from saya.config.ts
pnpm verify # drift check + typecheck + build/help + MCP smokepnpm smoke always checks unauthenticated protected-resource metadata. Set
SAYA_MCP_BEARER to additionally assert the authenticated tools/list surface.
License
MIT © creative-int
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/creative-int/saya-plugins'
If you have feedback or need assistance with the MCP directory API, please join our Discord server