mcpField
G
gjalla

gjalla

Remote
gjalla.ioMemory & Knowledge3Updated 5w ago
RepositoryVisit website

About gjalla

gjalla is a hosted shared-memory service for agents, described as self-curating. This repository provides its public MCP manifest and integration documentation; the server itself runs in gjalla's proprietary web service.

Key features

  1. 01Hosted shared memory for agents
  2. 02Self-curating shared memory
  3. 03Public MCP Registry manifest
  4. 04Integration documentation

Use cases

  1. 01Connect an MCP client to gjalla
  2. 02Use shared memory across agents
  3. 03Configure access with a bearer token

MCP support

gjalla provides a remote MCP server at https://gjalla.io/mcp/stream. MCP clients authenticate with a bearer token generated through the gjalla account page.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gjalla.io/mcp/stream
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://gjalla.io/mcp/streamAuth required

Tools

Details

From the project README

gjalla MCP server manifest

This folder hosts the server.json manifest for the gjalla MCP server, published to the official MCP Registry and crawled by downstream MCP directories.

Install

This surfaces gjalla's remote MCP server. Point your MCP client at:

https://gjalla.io/mcp/stream

Auth: Bearer token via the Authorization header. Generate an API key at https://gjalla.io/account/api-keys.

Source

The MCP server is hosted in the gjalla web service (proprietary). This repo holds the public manifest, skills, and integration docs.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.