Skip to main content
Glama

Run an admin command

admin
Destructive

Execute admin commands on a mesh node—read status, configure settings, or perform sensitive actions. Use dry run to preview.

Instructions

Run one enumerated admin command against a node. node is the home node (its name or key prefix) or a remote repeater (name / hex prefix). Pass dryRun: true to preview the intent without contacting the device. Each command carries a risk tier (surfaced in the result). Commands: Read: • ver [remote] — no params • board [remote] — no params • clock [remote] — no params • neighbors [remote] — no params • get-config [remote] — key: config key to read; prv.key is intentionally excluded (firmware blocks remote read for security)

Benign: • advert [home+remote] — mode: flood (mesh-wide) or zerohop (neighbours only) • sync-time [home+remote] — no params • log-start [remote] — no params • log-stop [remote] — no params • set-time [remote] — epochSecs: absolute time as epoch seconds (firmware rejects backwards clocks) • discover-neighbors [remote] — no params

Config: • set-tx-power [home+remote] — dbm: transmit power in dBm, 1–22 • set-radio [home+remote] — freqMhz: centre frequency in MHz (e.g. 910.525); kHz/Hz also accepted, bwKhz: bandwidth in kHz (sub-GHz: 62.5, 125, 250, 500; 2.4GHz/SX128x goes higher, up to 1000); Hz (62500) also accepted, sf: spreading factor, 5–12, cr: coding rate 5–8 (the 'n' in 4/n); '4/5' also accepted • set-name [home+remote] — name: advertised name, ≤32 bytes • set-location [home+remote] — lat: latitude in degrees, lon: longitude in degrees • set-repeat [remote] — enabled: true to enable packet repeating • set-dutycycle [remote] — percent: duty-cycle limit, 1–100 (percent) • set-path-hash-mode [remote] — mode: path-hash mode 0|1|2 (1-byte/2-byte/3-byte advertised prefixes; 64/32/21 flood cap respectively) • set-loop-detect [remote] — level: loop-detection aggressiveness • set-flood-max [remote] — hops: max flood hop count, 0–64 • set-radio-rxgain [remote] — enabled: true to enable boosted RX gain • tempradio [remote] — freqMhz: centre frequency in MHz (e.g. 910.525); kHz/Hz also accepted, bwKhz: bandwidth in kHz (sub-GHz: 62.5, 125, 250, 500; 2.4GHz/SX128x goes higher, up to 1000); Hz (62500) also accepted, sf: spreading factor, 5–12, cr: coding rate 5–8 (the 'n' in 4/n); '4/5' also accepted, timeoutMins: auto-revert timeout in minutes (≥1) • set-tx-delay [remote] — factor: TX delay factor 0–2 • set-direct-tx-delay [remote] — factor: direct TX delay factor 0–2 • set-rx-delay [remote] — secs: RX processing delay 0–20s • set-airtime-factor [remote] — factor: airtime factor 0–9 • set-interference-threshold [remote] — value: interference threshold (firmware-defined units) • set-agc-reset-interval [remote] — secs: AGC reset interval in seconds; firmware rounds to a multiple of 4 (0 disables) • set-multi-acks [remote] — enabled: true to enable multi-ack support • set-flood-advert-interval [remote] — hours: flood-advert interval in hours, 3–168 • set-advert-interval [remote] — minutes: zero-hop advert interval in minutes, 60–240; firmware stores it as /2 (use even values) • set-owner-info [remote] — text: owner info shown in adverts; '|' in the string becomes a newline • set-adc-multiplier [remote] — value: ADC multiplier 0.0–10.0 (0 = board default) • powersaving [remote] — enabled: true to enable sleep-between-TX power saving • region [remote] — sub: status | save | allowf (region: region name (prefix-matched)) | denyf (region: region name (prefix-matched)) | get (region: region name (prefix-matched)) | home-get | home-set (region: region name to set as home) | default-get | default-set (region: region name to set as default; use '' to clear) | put (name: new region name, parent: optional parent region; defaults to wildcard) | remove (region: region name (exact match)) | list-allowed | list-denied • gps [remote] — sub: status | on | off | sync | setloc | advert-get | advert-set (policy: none | share | prefs) • sensor [remote] — sub: get (key: sensor setting key to read) | set (key: sensor setting key to write, value: new value (string-typed; firmware parses per setting)) | list (startIndex: optional pagination start index (134-char chunks))

Sensitive (writes secrets / grants access): • set-admin-password [remote] — password: new admin password, ≤15 chars • set-permission [remote] — pubKey: hex public key, level: guest|read|readwrite|admin, or null to revoke (downgrade to guest — the firmware has no explicit removal, only a level-0 demotion) • set-allow-read-only [remote] — enabled: true to enable read-only mode • set-guest-password [remote] — password: new guest password, ≤15 chars

Destructive (data/identity loss or reboot): • reboot [home+remote] — no params • log-erase [remote] — no params • clear-stats [remote] — no params • remove-neighbor [remote] — pubKeyPrefix: hex public-key prefix • set-private-key [remote] — hex: new private key as 64 hex chars (32 bytes) • start-ota [remote] — no params • clkreboot [remote] — no params

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nodeYes
commandYesthe admin command name (see the catalogue in this description); an unknown name returns the valid list
paramsNo
dryRunNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYes
tierYes
annotationsYesthe deterministic per-command risk hints this tier maps to; surfaced here (not as MCP tool-level annotations) because `admin` is one multiplexed tool
dryRunYes
viaNo
previewNo
replyNo
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite annotations indicating destructive behavior, the description adds significant context: it categorizes commands by risk tier (Read, Benign, Config, Sensitive, Destructive), explains the dryRun flag for previewing effects, and provides specific behavioral notes (e.g., firmware rejecting backwards clocks, key exclusion for security).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with a clear summary and then structured into categorized command blocks. While lengthy, every sentence serves to document a command or parameter, making it efficient for its purpose. Could be further optimized but remains functional.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (many commands, nested parameters, output schema), the description covers all aspects: command catalog, parameter details, dryRun behavior, risk tiers, and error handling (unknown command returns valid list). The output schema is separate, so completeness is high.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has low coverage (25%), but the description fully compensates by enumerating every valid command and its sub-parameters with detailed syntax and constraints. This adds immense meaning beyond the minimal schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the purpose: 'Run one enumerated admin command against a node.' It specifies the resource (admin commands) and the action (run against a node). The extensive list of commands distinguishes this tool from sibling tools that target specific operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context for when to use the tool (to run admin commands) but does not explicitly exclude alternatives or guide when to use sibling tools instead of this general tool. The listing of commands implies coverage, but no direct guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dpup/meshcore-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server