Skip to main content
Glama
plan5-labs

sila2-mcp

by plan5-labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SILA2_MCP_CONFIGNoPath to another servers configuration file, alternative to editing servers.toml or using --config.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_serversA

List the configured SiLA 2 servers and whether each one answers right now.

Read-only. Tries to connect to each server; a server that does not answer is reported with its error instead of failing the whole call.

describe_serverA

Describe one server's features: commands (observable or not, parameters, responses, intermediate responses, defined errors) and properties, with their FDL descriptions.

Read-only. Use it to learn parameter names and types before call_command.

get_propertyB

Read a property's current value once (observable properties too).

Read-only. feature is needed only when two features of the server share the property name.

call_commandA

Run a SiLA 2 command and return its responses. MAY MOVE HARDWARE.

parameters maps parameter identifiers to values, e.g. {"BucketNumber": 1}. An observable command is waited for until it finishes or timeout_s passes; its intermediate responses are collected and returned. On failure, ok is false and error holds the SiLA error (defined execution error identifier and message). feature is needed only when two features of the server share the command name.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation5/5

Each tool targets a distinct layer: list_servers for discovery, describe_server for introspection, get_property for reading a value, and call_command for execution. There is no meaningful overlap—describe_server describes schema while get_property returns a live value, and the descriptions make this clear.

Naming Consistency5/5

All four names follow a clean verb_noun snake_case pattern (list_servers, describe_server, get_property, call_command). The convention is predictable and unambiguous.

Tool Count4/5

Four tools map neatly onto the core SiLA 2 interaction loop (discover, inspect, read, execute), and each earns its place. It is on the lean side—no streaming or cancellation tool—but not thin for the essential scope.

Completeness4/5

The set covers discovery, introspection, property reads, and command execution with observable-command waiting and error reporting, which is a coherent lifecycle. Minor gaps remain: no subscription to observable property streams and no explicit command cancellation, but agents can work around these via repeated reads and timeouts.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources