About Steledger
Steledger is an MCP server that lets AI agents use the Emercoin chain for identity and memory through an edge gateway API. Its tools cover authentication, identity registration, memory storage, and record retrieval.
Key features
- 01Check gateway node status
- 02Authenticate through GitHub device flow
- 03Register an identity with metadata
- 04Store individual or batched memory records
- 05Read a record by name
Use cases
- 01Check whether the gateway is available
- 02Sign in before identity or memory operations
- 03Register an agent identity
- 04Store or retrieve memory records
MCP support
Provides tools for MCP clients to interact with the edge gateway, including authentication and Emercoin-backed identity and memory operations. It runs over stdio.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.steledger.com/mcpclaude mcp add --transport http com-steledger-gateway https://api.steledger.com/mcp{"mcpServers":{"com-steledger-gateway":{"type":"http","url":"https://api.steledger.com/mcp"}}}Open in Cursor{"servers":{"com-steledger-gateway":{"type":"http","url":"https://api.steledger.com/mcp"}}}Open in VS Code{"mcpServers":{"com-steledger-gateway":{"type":"http","url":"https://api.steledger.com/mcp"}}}{"mcpServers":{"com-steledger-gateway":{"serverUrl":"https://api.steledger.com/mcp"}}}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.
https://api.steledger.com/mcpAuth requiredghcr.io/steledger/mcp:lateststdioTools
9This tool takes no parameters.
Details
From the project READMESteledger — MCP server
Thin MCP client over the edge gateway HTTP API. Lets an AI agent use the
Emercoin chain as its identity + memory layer. (The edge is the agent-facing IAM
layer; it delegates chain ops to the node adapter — see docs/ARCHITECTURE.md.)
Tools
| Tool | Auth | Maps to |
|---|---|---|
node_status() | no | GET /status |
login() | no | POST /auth/github/device/start (device flow; show code to user) |
login_poll(session_id) | no | POST /auth/github/device/poll (finish; caches JWT) |
login_with_token(github_token) | no | POST /auth/login (dev/CI fallback) |
register_identity(address, metadata?) | yes | POST /nvs/identity |
store_memory(content_hash, metadata?) | yes | POST /nvs/mem |
store_memory_batch(records) | yes | POST /nvs/mem/batch (atomic, one tx) |
read_record(name) | no | GET /nvs/{name} |
Config (env)
GATEWAY_URL— edge gateway base URL (defaulthttp://localhost:8000)GATEWAY_JWT— optional pre-issued token; otherwise use thelogintool
Run (stdio transport)
pip install -r requirements.txt
GATEWAY_URL=http://localhost:8000 python server.py
Claude Code MCP config example
{
"mcpServers": {
"steledger": {
"command": "python",
"args": ["/path/to/mcp_server/server.py"],
"env": { "GATEWAY_URL": "http://localhost:8000" }
}
}
}
Comments
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.