Skip to main content
Glama
wtnb75

rrdmcp

by wtnb75
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MUNIN_DATAFILE_PATHNoLocation of Munin's datafile (config cache)${MUNIN_RRD_BASE_PATH}/datafile
MUNIN_RRD_BASE_PATHNoRoot directory of the RRD files/var/lib/munin

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
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_hostsA

List all (group, host) pairs discovered from the Munin datafile.

list_pluginsB

List plugins for a given host.

list_fieldsC

List fields for a given plugin.

get_metadataB

Get metadata for a plugin, or a single field within it if field is given.

fetch_seriesA

Fetch time series data for a single field.

start/end accept a unix timestamp or any string rrdtool understands (e.g. "-1d", "now").

If resolution (seconds) is given, points are aggregated into UTC-epoch-aligned buckets of that size (avg/min/max/count) instead of returning every raw sample — use this for long time ranges to avoid returning hundreds of raw points.

If summary is true, the whole range is aggregated into a single avg/min/max/count instead of buckets or raw points. Cannot be combined with resolution.

If top_n is given (requires resolution), only the N buckets with the highest (or, with order="asc", lowest) top_by value ("avg", "min", or "max") are returned, sorted by that value; total_buckets in the result reports how many buckets existed before filtering.

render_graphC

Render a PNG graph overlaying the given fields of a plugin.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 6 tools

Disambiguation5/5

Each tool targets a distinct level or aspect of the data hierarchy: hosts, plugins, fields, metadata, series data, and rendered graphs. There is no meaningful overlap between tools, and descriptions make the boundaries clear.

Naming Consistency5/5

All tool names follow the same snake_case verb_noun pattern, with list_* for enumeration, get_/fetch_ for retrieval, and render_ for graph generation. The naming is predictable and consistent across the whole set.

Tool Count5/5

With 6 tools, the set is well-scoped for a read-only RRD/Munin data access server. Each tool covers an essential operation without unnecessary redundancy or bloat.

Completeness5/5

The tool set covers the full exploration and retrieval workflow: discover hosts, list plugins, list fields, fetch metadata, fetch time series data, and render graphs. There are no significant dead ends or missing operations for the apparent purpose of reading monitoring data.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources