Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Tactical RMM MCP

MCPB · TACTICAL-RMM-MCP.MCPB

Every Tactical RMM endpoint as a typed command, plus an offline SQLite mirror and cross-entity

+1 this week 50 Trust /100

Last scanned (15 hours ago)

Scores higher than 81% of MCPB servers

Category Cloud Infrastructure

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security0
  • No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
  • Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 12 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability52
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 36881 tokens (~472/item across 78 items; 78 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management99
  • Stability check failed: the tool surface changed between 0.1.3 and 0.1.7: 0 tool removals, 1 breaking changes, 0 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety81
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agents_shutdown" implies "shutdown" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 78 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (12)

  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (4)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  • Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  • Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
  • Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 96 to 99.

  • 29 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 89 to 93.

  • 27 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 86.

  • 25 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 76 to 79.

  • 23 Oct 26 +2
    • Provenance: fail → unverified ▼ security
    • Stability: 0.70 → fail ▼ security
    • Schema quality: 528 → 472 ▲ functional
    • Package version: 0.1.5 → 0.1.7 functional
    • Package version: 0.1.5 → 0.1.6 functional
  • 22 Oct 26 +1
    • Stability: 0.67 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
    • Package version: 0.1.4 → 0.1.5 functional
    • Package version: 0.1.3 → 0.1.4 functional
  • 20 Oct 26 +2
    • Maintenance: unverified → pass ▲ functional
  • 19 Oct 26 0
    • Package version: 0.1.3 → 0.1.4 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Analysed mcpb/https://github.com/Servosity/msp-skills/releases/download/tactical-rmm-v0.1.7/tactical-rmm-mcp.mcpb@0.1.7

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem mcpb
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 78 exposed · ~36,881 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
orphans ~507

Scan locally synced data for items that are missing important fields such as assignee, project, priority, or labels. Useful for triaging unowned work.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
limitnumber–Maximum items to show (default: 50)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

patch ~476

Roll pending Windows updates and reboots up to each client or site from the local store.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

patch_posture ~515

Rolls pending Windows updates and reboots up to each client or site from the local store. For a per-client posture row across all signals (not just patches), use 'clients scorecard'.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
bystring–Group by: client or site (default: client)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

scripts ~468

Get, create, update, and delete scripts

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

scripts_download ~465

Run download operations for scripts

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

scripts_test ~464

Create test for scripts

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

search ~64

Full-text search across all synced data. Faster than paginating list endpoints. Requires sync first.

NameTypeReqDescription
limitnumber–Max results (default 25)
querystringyesSearch query (supports FTS5 syntax: AND, OR, NOT, quotes for phrases)

No output schema declared.

No examples provided.

services ~466

Get, create, and update services

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

services_down ~569

Use this command to find agents where a named Windows service is stopped. Do NOT use it to find installed software packages; use 'software find' instead. Services are not stored locally, so this fans out live to GET /services/{agent_id}/ for each synced agent, capped by --max-scan-agents. Read-only.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
max-scan-agentsnumber–Max agents to fan out to live (default: 50)
namestring–Windows service name (required), e.g. Spooler
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

since ~546

Reports new alerts and newly-offline agents within the window (e.g. 2h, 24h, 7d), derived from synced timestamps. Reads only the local store.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
argsstring–Additional positional arguments or raw CLI flags to append to the command.
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
windowstring–Time window (e.g. 2h, 24h, 7d) (default: 24h)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

software ~466

Get, create, and update software

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

software_find ~537

Searches synced per-agent software inventory for a package name (case-insensitive substring) and lists each agent, version and publisher. Reads only the local store. To find agents where a Windows service is stopped instead, use 'services down'.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
argsstring–Additional positional arguments or raw CLI flags to append to the command.
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
namestring–Package name to search for
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

software_uninstall ~465

Create uninstall for software

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

sql ~93

Run read-only SQL against local database. Use for ad-hoc analysis, aggregations, and joins across synced resources. Requires sync first.

NameTypeReqDescription
querystringyesSQL query (SELECT or WITH...SELECT). Synced records live in resources(resource_type, id, data); filter by resource_type and use json_extract on data, e.g. SELECT json_extract(data,'$.name') FROM reso…

No output schema declared.

No examples provided.

stale ~532

Scan locally synced data for items that have not been updated within the specified number of days. Useful for identifying forgotten or blocked work.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
daysnumber–Number of days without update to consider stale (default: 30)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
limitnumber–Maximum items to show (default: 50)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
teamstring–Filter by team identifier
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

sync ~1,164

Sync data from the API into a local SQLite database. Supports resumable incremental sync (only fetches new data since last sync) and full resync. Once synced, use the 'search' command for instant full-text search. Exit codes & warnings: Resources the API denies access to (HTTP 403, or HTTP 400 with an access-policy body) are reported as warnings rather than failing the run. In --json mode each is emitted as a {"event":"sync_warning",...} line carrying status, reason, and message fields, and a final {"event":"sync_summary",...} aggregates the run. Exit 0 when at least one resource synced and no resource flagged in the spec as critical (x-critical: true) failed; non-critical failures emit {"event":"sync_warning","reason":"exit_policy_default_changed", ...} so callers can detect that a partial failure was tolerated. Pass --strict to exit non-zero on any per-resource failure. Exit is always non-zero when every selected resource failed, regardless of --strict. Resource scoping: --resources runs the named top-level resources, plus any parent-keyed dependent whose own name is listed OR whose parent table is listed. Naming a parent therefore cascades to its dependents (so "sync this parent and its children" works without listing every nested resource by hand). There is no flag today to suppress the cascade for a named parent. To run a dependent without re-syncing its parent, list only the dependent by name; the parent table must already be populated from a prior sync.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
concurrencynumber–Number of parallel sync workers (default: 4)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
fullboolean–Full resync (ignore previous checkpoint) (default: false)
global-paramstring–Extra query param to inject into every sync request including dependent path-scoped calls (repeatable, key=value). Use when an API requires a scope on every call regardless of path nesting.
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
latest-onlyboolean–Refresh head of each resource only; clears resume cursor and caps pages at 1. Mutually exclusive with --since (--since wins). (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
max-pagesnumber–Maximum pages to fetch per resource (0 = unlimited; cap-hit emits a sync_warning event) (default: 0)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
paramstring–Extra query param to inject into flat-list sync requests (repeatable, key=value). Skipped on path-scoped dependent requests so a top-level scope like workspace=<id> does not double up on /parents/<id…
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
resource-paramstring–Per-resource extra query param (repeatable, resource:key=value). Wins over --param and --global-param when keys conflict.
resourcesstring–Comma-separated resource types to sync. Naming a parent also runs its parent-keyed dependents (see Long help for scoping).
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
sincestring–Incremental sync duration (e.g. 7d, 24h, 1w, 30m)
strictboolean–Exit non-zero on any per-resource failure (default: only critical failures or all-resource failure exit non-zero). (default: false)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

tactical-rmm_execute ~104

Execute one tactical-rmm API endpoint by its endpoint_id (from tactical-rmm_search). Params are passed as a JSON object; path placeholders and query strings are resolved automatically.

NameTypeReqDescription
endpoint_idstringyesEndpoint identifier returned by tactical-rmm_search (e.g., "users.list").
paramsobject–Parameters for the endpoint. Path placeholders match by name; remaining entries become query string on GET/DELETE or JSON body on POST/PUT/PATCH.

No output schema declared.

No examples provided.

tactical-rmm_search ~82

Search the tactical-rmm API for endpoints matching a natural-language query. Returns a ranked list of {endpoint_id, method, path, summary} entries. Call this first to find the endpoint to execute.

NameTypeReqDescription
limitnumber–Max endpoints to return (default 10).
querystringyesNatural-language description of what you want to do.

No output schema declared.

No examples provided.

tail ~586

Tail streams live data changes by polling the API at configurable intervals. Events are emitted as NDJSON to stdout for piping to other tools. Gracefully shuts down on SIGTERM/SIGINT. Note: For APIs with WebSocket or SSE support, a future version will use native streaming instead of polling.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
argsstring–Additional positional arguments or raw CLI flags to append to the command.
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
followboolean–Keep running (set --follow=false for single poll) (default: true)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
intervalstring–Poll interval (default: 10s)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
resourcestring–Resource type to tail
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

triage ~526

Scores every synced agent across offline state, failing checks, pending reboots, patches and pending actions, then ranks them. Use this to rank individual agents by how much attention they need. To rank failing checks by blast radius instead, use 'checks worst'.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
limitnumber–Max agents to return (default: 25)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

winupdate ~465

Get and update winupdate

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

winupdate_install ~466

Create install for winupdate

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

winupdate_scan ~466

Create scan for winupdate

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

workflow ~466

Compound workflows that combine multiple API operations

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

workflow_archive ~530

Archive fetches all syncable resources from the API and stores them in a local SQLite database. Supports incremental sync (only new data since last run) and full resync. After archiving, use 'search' for instant full-text search.

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
fullboolean–Full re-archive (ignore previous sync state) (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

workflow_status ~470

Show local archive status and sync state for all resources

NameTypeReqDescription
agentboolean–Set all agent-friendly defaults (--json --compact --no-input --no-color --yes) (default: false)
allow-partial-failureboolean–Downgrade response-body partial-failure (e.g. partialFailureError) to a warning instead of a non-zero exit (default: false)
compactboolean–Return only key fields (id, name, status, timestamps) for minimal token usage (default: false)
csvboolean–Output as CSV (table and array responses) (default: false)
data-sourcestring–Data source for read commands: auto (live with local fallback), live (API only), local (synced data only) (default: auto)
dry-runboolean–Show request without sending (default: false)
human-friendlyboolean–Enable colored output and rich formatting (default: false)
idempotentboolean–Treat already-existing create results as a successful no-op (default: false)
ignore-missingboolean–Treat missing delete targets as a successful no-op (default: false)
jsonboolean–Output as JSON (default: false)
max-agestring–Maximum acceptable age of local-store data before a stderr hint suggests sync; 0 disables (default: 30m0s)
no-cacheboolean–Bypass response cache (default: false)
no-colorboolean–Disable colored output (default: false)
no-inputboolean–Disable all interactive prompts (for CI/agents) (default: false)
plainboolean–Output as plain tab-separated text (default: false)
quietboolean–Bare output, one value per line (default: false)
rate-limitnumber–Max requests per second (0 to disable) (default: 0)
selectstring–Comma-separated fields to include in output (e.g. --select id,name,status)
timeoutstring–Request timeout (default: 1m0s)
yesboolean–Skip confirmation prompts (for agents and scripts) (default: false)

No output schema declared.

No examples provided.

Install

How do I install the Tactical RMM MCP server?

Tactical RMM MCP ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 6cd95d0b34683b8efc9f36961c06d45a818d8bbc8af2fb0da4b18ffdf7f674cd; the commands to do that are on this page. If it does not match, do not open it.

mcpb · tactical-rmm-mcp.mcpb

Download bundle

Check the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.

SHA-256

6cd95d0b34683b8efc9f36961c06d45a818d8bbc8af2fb0da4b18ffdf7f674cd

macOS / Linux

echo "6cd95d0b34683b8efc9f36961c06d45a818d8bbc8af2fb0da4b18ffdf7f674cd  tactical-rmm-mcp.mcpb" | shasum -a 256 -c

Windows (PowerShell)

(Get-FileHash -Algorithm SHA256 .\tactical-rmm-mcp.mcpb).Hash -eq "6cd95d0b34683b8efc9f36961c06d45a818d8bbc8af2fb0da4b18ffdf7f674cd"

Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.

Common questions

What is the Tactical RMM MCP server?

Tactical RMM MCP is listed in the public MCP registry as io.github.Servosity/tactical-rmm-mcp. Every Tactical RMM endpoint as a typed command, plus an offline SQLite mirror and cross-entity. This page covers its MCPB bundle (https://github.com/Servosity/msp-skills/releases/download/tactical-rmm-v0.1.7/tactical-rmm-mcp.mcpb).

Is the Tactical RMM MCP server safe to use?

Tactical RMM MCP scores 50 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Tactical RMM MCP server expose?

Tactical RMM MCP exposes 78 tools: accounts, accounts_users, actions, actions_pending, agents, and 73 more. Their descriptions and schemas cost roughly 36,881 tokens of context every time the server is loaded.

What licence is the Tactical RMM MCP server under?

Tactical RMM MCP declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Tactical RMM MCP server?

VerifyMCP ran 12 checks on Tactical RMM MCP, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about Tactical RMM MCP: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.