Sphinx gives agents access to approved internal knowledge, including company context, process guidance, metric definitions, customer context, and marketing information. This repository bundles the Sphinx knowledge-base instructions with the Sphinx MCP server configuration.
Sphinx can be installed either as a plugin in supported clients (recommended) or as a standalone MCP connector.
Client-specific installation instructions are provided below. Note that only users with pre-existing Sphinx accounts can use this plugin. If you are interested in trying Sphinx, contact our sales team.
Configure your MCP client to connect to the following MCP server URL:
https://api.prod.sphinx.ai/mcp
The bundled MCP configuration registers the server as sphinx:
The Sphinx MCP server relies on OAuth authentication with Dynamic Client Registration (DCR). Most up-to-date MCP clients should support this out-of-the-box with no additional configuration.
search: Search the Sphinx knowledge base with a natural-language query. Use vector search for conceptual questions and keyword search for exact terms.fetch: Retrieve the full text of a knowledge base page. Must follow a call to search.suggest_edits: Ask Sphinx to asynchronously improve the knowledge base based on natural-language guidance. The tool returns a URL where the created job can be monitored.If you encounter other issues, please contact our support team at [email protected].
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub sphinx-ml/sphinx-plugin --plugin sphinxGive your AI a memory — mine projects and conversations into a searchable palace. 33 MCP tools, auto-save hooks, and guided setup.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
Write SQL, explore datasets, and generate insights faster. Build visualizations and dashboards, and turn raw data into clear stories for stakeholders.
MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.