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

io.github.rharper105/reportcraft

NPM · @REPORTCRAFT/MCP-SERVER · SCANNED AUG 3

Generate Splunk dashboards, reports, and alerts from natural language. No API key required.

+21 this week 61 Trust /100
Trust breakdown (6 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 →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (108 of 112), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (108 of 112), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 632 tokens (~90/item across 7 items; 7 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @reportcraft/mcp-server

# add to Claude Code
claude mcp add rharper105-reportcraft -- npx -y @reportcraft/mcp-server
# add to Codex CLI
codex mcp add rharper105-reportcraft -- npx -y @reportcraft/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rharper105-reportcraft": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@reportcraft/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add rharper105-reportcraft --command npx --arg -y --arg @reportcraft/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  rharper105-reportcraft:
    command: "npx"
    args: ["-y", "@reportcraft/mcp-server"]
// mcp.json
{
  "mcpServers": {
    "rharper105-reportcraft": {
      "command": "npx",
      "args": [
        "-y",
        "@reportcraft/mcp-server"
      ]
    }
  }
}
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.

  • 2 Aug 26 +45
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • License: unverified → fail functional
    • Schema quality: unverified → excellent functional
    • Dependency health: unverified → partial functional
    • Stability: unverified → 0.20 functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
  • 1 Aug 26 +16
    • Tool coverage: unverified → 100 functional
  • 31 Jul 26 −22
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 40

    First indexed and scored.

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 3 Aug 2026 · Analysed npm/@reportcraft/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 108 packages

108 packages in the resolved dependency tree · 108 deprecated · 39 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 7 exposed · ~632 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.

Tool Tokens
export_package ~82

Generate a complete Splunk export package from a blueprint. Returns a ZIP containing Classic XML dashboard, Studio JSON, savedsearches.conf, SPL queries, field mapping, and import guide.

NameTypeReqDescription
blueprintobjectyesA ReportBlueprint object (ideally with SPL generated via generate_spl)
optionsobjectExport options (all default to true if omitted)

No output schema declared.

No examples provided.

generate_blueprint ~142

Generate a complete ReportBlueprint from a structured intent, field catalog, and data source. The blueprint defines panels, layout, datasets, and field mappings for a Splunk dashboard, report, or alert.

NameTypeReqDescription
clarificationsarrayAnswered clarification questions
confirmedMappingsobjectUser-confirmed field mappings (fieldId → role assignments)
dataSourceobjectyesSplunk data source configuration
fieldCatalogarrayyesArray of field definitions with id, sourceName, type, and semanticRole
intentobjectyesStructured intent from parse_intent
rawPromptstringyesThe original natural language prompt

No output schema declared.

No examples provided.

generate_spl ~49

Generate SPL queries for each panel in a ReportBlueprint. Takes a blueprint and returns it with generatedSpl populated on each panel.

NameTypeReqDescription
blueprintobjectyesA ReportBlueprint object from generate_blueprint

No output schema declared.

No examples provided.

parse_intent ~75

Parse a natural language description of a Splunk dashboard, report, or alert into a structured intent. Returns audience, use case, layout preference, and time range.

NameTypeReqDescription
rawPromptstringyesNatural language description of what the user needs (e.g., 'Failed auth monitoring with trends by hour and top risky IPs')

No output schema declared.

No examples provided.

splunk_connect ~92

Connect to a Splunk instance via REST API. Tests the connection and returns server info. Credentials stay in-memory for this session only — never persisted.

NameTypeReqDescription
baseUrlstringyesSplunk management URL (e.g., 'https://localhost:8089' or 'https://splunk.corp.local:8089')
tokenstringyesSplunk password or auth token for the admin user

No output schema declared.

No examples provided.

splunk_deploy ~102

Deploy a generated blueprint to the connected Splunk instance. Creates the dashboard and any saved searches/alerts. Requires splunk_connect first.

NameTypeReqDescription
appNamestringSplunk app to deploy into (default: 'search')
blueprintobjectyesA ReportBlueprint with SPL generated (from generate_spl)
dashboardNamestringName for the dashboard in Splunk (lowercase, underscores). Auto-generated from blueprint title if omitted.

No output schema declared.

No examples provided.

splunk_discover ~90

Discover the schema of a connected Splunk instance — indexes, sourcetypes, and fields. Returns structured data that feeds directly into generate_blueprint. Requires splunk_connect first.

NameTypeReqDescription
indexstringSpecific index to discover fields from. If omitted, returns all indexes with event counts.
sourcetypestringFilter field discovery to a specific sourcetype within the index.

No output schema declared.

No examples provided.