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.

HOI4 Agent Tools

NPM · HOI4-AGENT-TOOLS

Build HOI4 mods: focus trees, events, decisions, worlds, GUI previews, docs and AI balance.

Available components

+11 this week 64 Trust /100

Last scanned (6 hours ago)

Scores higher than 37% of npm servers

Category Entertainment and Games

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 Security39
  • Malware scan not yet available for this package.Unverified
  • CVE check failed: a known medium-severity CVE affects glob 13.0.6, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 41 of 166 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to klimPaskov/hoi4-agent-tools). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability73
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2045 tokens (~146/item across 14 items; 13 tools + 1 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 Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage72
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 1% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • 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 (1)

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 SecurityMalware scan not yet available for this package.

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.

  • 21 Nov 26 −12
    • Malware scan: pass → unverified ▼ security
    • Stability: unverified → 0.23 ▲ functional
    • Package version: 4.18.0 → 4.19.0 functional
  • 15 Nov 26 +23
    • Known CVEs: unverified → fail ▼ security
    • Malware scan: unverified → pass ▲ security
    • Dependency health: unverified → 0.89 ▲ functional
  • 14 Nov 26 +6
    • Known CVEs: fail → unverified ▼ security
    • Malware scan: pass → unverified ▼ security
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Dependency health: 0.89 → unverified ▼ functional
    • Tool coverage: unverified → 100 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Schema quality: unverified → 100 ▲ functional
    • First check of Schema quality: fail functional
    • First check of Tool coverage: 1 functional
    • First check of Destructive annotations: pass functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: good functional
    • First check of Tool coverage: 100 functional
    • Package version: 4.16.0 → 4.18.0 functional
    • Package version: 4.16.0 → 4.17.0 functional
  • 13 Nov 26 +1
    • Package version: 4.15.0 → 4.16.0 functional
  • 10 Nov 26 0
    • Stability: Stability not yet verified: our sandbox could not run this package, so we have no schema to compare. security
    • Tool safety: Tool safety not yet verified: our sandbox could not run this package, so we have no tool text to scan. security
    • Schema quality: Schema quality not yet verified: our sandbox could not run this package, so we have no schema to assess. functional
    • Capabilities: Protocol version not yet verified: our sandbox could not run this package, so we never saw its MCP handshake. functional
    • Tool coverage: Tool coverage not yet verified: our sandbox could not run this package, so we have no tool definitions to assess. functional
  • 9 Nov 26 +7
    • Known CVEs: unverified → fail ▼ security
    • Provenance: pass → unverified ▼ security
    • Tool safety: Tool safety not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Dependency health: unverified → 0.88 ▲ functional
    • Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet. functional
    • Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. 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: 4.12.0 → 4.15.0 functional
    • Package version: 4.12.0 → 4.14.0 functional
    • Package version: 4.12.0 → 4.13.0 functional
  • 8 Nov 26 −7
    • Known CVEs: fail → unverified ▼ security
    • Provenance: pass → unverified ▼ security
    • Dependency health: 0.88 → unverified ▼ functional
    • Package version: 4.11.0 → 4.12.0 functional
    • Package version: 4.11.0 → 4.11.1 functional
  • 7 Nov 26 +7
    • Known CVEs: unverified → fail ▼ security
    • Dependency health: unverified → 0.88 ▲ functional
    • Package version: 4.10.0 → 4.11.0 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 21 Nov 2026 · Analysed npm/hoi4-agent-tools@4.19.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo klimPaskov/hoi4-agent-tools
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/klimPaskov/hoi4-agent-tools/.github/workflows/release.yml@refs/tags/v4.19.0
Rekor log index 4033694058
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:a071a9c4ab75cf3e106b6e09e37d4c8eb442ccab3ecf3a92308d7d5988f91e06c539656705b2b11643f03e57e8e6baa1882a75b23288c3af3f1f0907d

Background: How many MCP packages publish verified provenance →

Vulnerabilities 3 findings
ID CVE Severity Vector Fix available
GHSA-rmxm-3fg6-px4f CVE-2026-118663 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N yes
GHSA-3g3m-2fjr-6pw4 CVE-2026-118773 medium yes
GHSA-g3hv-75wg-m249 CVE-2026-118764 medium yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 166 packages
Packages resolved 166
Stale 41
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~1,823 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
hoi4.error_log ~132

Find errors from the last game launch and group them by category, with source files, lines and fix hints. Show which files changed since the log and which errors appeared after a relaunch; mod entries come first. Example: {"scope":"mod","category":"effect"}. Returns at most 20 entries (limit 50) with fix hints and which entries are new since the previous launch.

NameTypeReqDescription
categorystring––
limitinteger––
offsetinteger––
querystring––
scopestring––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.explain_error ~116

Explain error.log lines: the rule each one breaks, its file and line with the lines around it, and the fix, from a reviewed catalogue of the game's messages. Says whether the game documents the command a line names, and the closest documented names. Example: {"line":"Invalid trigger 'stability' in events/my_events.txt line : 12"}. Returns up to 20 explanations (10 lines).

NameTypeReqDescription
linestring––
linesarray––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.localisation_inspect ~150

Read localisation in every language the game and mod ship. key: one key per language with file, line and layer, the languages lacking it and the files mentioning it. audit: keys the mod uses that no language defines, keys missing from a supported language, keys defined twice in one language, and file problems. coverage: keys per language. Example: {"mode":"key","key":"my_event.1.t"} or {"mode":"audit"}. Returns counts per problem and a few examples of each.

NameTypeReqDescription
keystring––
languagestring––
limitinteger––
modestring––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.localisation_write ~186

Add localisation keys (mode add: key and text; language, file, replace) or repair localisation files (mode fix: BOM, broken quotes, keys missing from supported languages). Game keys are overridden from a replace folder. apply false returns the diff and writes nothing; apply true writes it. Returns up to 10 files with diffs. Example: {"mode":"add","entries":[{"key":"my_focus","text":"My focus"}]}

NameTypeReqDescription
applyboolean–false returns the diff and writes nothing; true makes the same change.
entriesarray––
filestring––
fixesarray––
languagestring––
modestringyes–
pathsarray––
replaceboolean––
requestKeystring––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.mod_health ~130

Check a whole mod in one call: the last error.log, the engine check (unknown effects, triggers and modifiers, duplicate ids, broken overrides), script validation, and the localisation and asset audits. Returns the 10 problems that matter most, each counted with 2 examples, its fix and the tool to use next, and which audits ran. Example: {"limit":5} or {"checks":["error_log","engine_check"]}. Takes up to a minute on a large mod.

NameTypeReqDescription
checksarray––
limitinteger––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.mod_index ~149

Summarize the content in a mod or find a free event ID across the mod, game and dependencies. Use overview for descriptors, folders and definitions (the 50 busiest namespaces; pass a namespace or prefix to list those starting with it), or next_id with a namespace or prefix. Example: {"mode":"next_id","kind":"event","namespace":"my_mod"}. Returns a compact summary; the first call indexes the mod, which takes seconds on a large one.

NameTypeReqDescription
kindstring––
layerstring––
modestring––
namespacestring––
prefixstring––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.reference_context ~99

Find documentation for the content you are building: events, decisions, ideas, focuses, technology, GUI, maps, localisation or AI. Example: {"surface":"event","question":"fire an event after a delay"}. Returns up to 16 short sections; read more with hoi4.reference_read.

NameTypeReqDescription
limitinteger––
questionstring––
surfacestringyes–
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.reference_read ~123

Read a documentation section returned by reference_search or reference_context. Pass its id and revision. Example: {"id":"<hit id>","revision":"<hit revision>"}. Returns at most 80 lines (40 by default) and 8,000 bytes, with a line to continue from.

NameTypeReqDescription
idstringyes–
maxLinesinteger––
revisionstringyes–
sourcestring––
startColumninteger––
startLineinteger––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.reference_search ~142

Find a modding rule in the offline wiki and installed game docs by plain words or script name. Returns up to 10 short candidates (limit up to 12) with file, lines, revision and, for a command, a one-line meaning and its scopes. Pick the one that fits, since several commands sound alike, then read it with hoi4.reference_read using its id and revision. Example: {"query":"add_timed_idea"} or {"query":"make a country hold elections now"}.

NameTypeReqDescription
limitinteger––
querystringyes–
sourcesarray––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.script_guard ~114

Check the files you wrote for invented commands: every effect, trigger and modifier that the installed game documentation does not list and no loaded file defines, with its file, line and the closest real name. Checks the named paths, or the mod script files changed in the last 120 minutes. Needs hoi4-engine. Example: {"paths":["events/my_events.txt"]}. Returns up to 40 names.

NameTypeReqDescription
pathsarray––
sinceMinutesinteger––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.script_validate ~159

Find broken syntax, commands and scopes in an effect, trigger or mod file using the installed docs. Unknown helpers and native argument blocks stay unresolved. Example: {"source":"add_political_power = 10","kind":"effect","scope":"country"} or {"path":"events/a.txt"}. {"closure":true} instead counts whether the references of the whole mod resolve, per kind. Returns up to 12 findings.

NameTypeReqDescription
bindingsarray––
closureboolean––
documentationstring––
kindstring––
limitinteger––
pathstring––
scopestring––
sourcestring––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.skill ~120

List the modding skills installed in the mod, or load one by name, at the kit version HOI4 Mod Setup pinned, with its hash. A file edited since Setup installed it is refused unless acceptLocalEdits. Example: {"name":"hoi4-events"}. Returns up to 20,000 bytes of text; continue from nextOffset.

NameTypeReqDescription
acceptLocalEditsboolean––
filestring––
namestring––
offsetinteger––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

hoi4.source_lookup ~203

Find where a script symbol is defined and used across the game, DLC and mod. Pass a symbol, or a file path and line. Example: {"symbol":"my_scripted_effect"}. Returns up to 3 definitions with source text and 10 usages; keyPath and view=structure navigate nested blocks.

NameTypeReqDescription
childOffsetinteger––
columninteger––
expectedRevisionstring––
fromColumninteger––
fromLineinteger––
includeReferencesboolean––
keyPatharray––
kindstring––
lineinteger––
maxChildreninteger––
maxDefinitionsinteger––
maxLinesinteger––
maxReferencesinteger––
pathstring––
symbolstring––
viewstring––
workspaceIdstring––
NameTypeReqDescription
artifactsarray––
blockersarray––
changedFilesarray––
codestringyes–
dataobjectyes–
diagnosticsarray––
filesScannedarray––
proposedFilesarray––
statusstringyes–
validation–yes–
workspaceIdstringyes–

No examples provided.

Install

How do I install the HOI4 Agent Tools MCP server?

HOI4 Agent Tools runs locally as an npm package, launched with npx -y hoi4-agent-tools. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · hoi4-agent-tools

# add to Claude Code
claude mcp add klimpaskov-hoi4-agent-tools -- npx -y hoi4-agent-tools
Common questions

What is the HOI4 Agent Tools MCP server?

HOI4 Agent Tools is an MCP server listed in the public MCP registry as io.github.klimPaskov/hoi4-agent-tools. Build HOI4 mods: focus trees, events, decisions, worlds, GUI previews, docs and AI balance. This page covers its npm package (hoi4-agent-tools).

Is the HOI4 Agent Tools MCP server safe to use?

HOI4 Agent Tools scores 64 out of 100 on VerifyMCP. We recorded 3 known advisories against it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 HOI4 Agent Tools MCP server expose?

HOI4 Agent Tools exposes 13 tools: hoi4.localisation_write, hoi4.reference_search, hoi4.reference_read, hoi4.reference_context, hoi4.source_lookup, and 8 more. Their descriptions and schemas cost roughly 1,823 tokens of context every time the server is loaded.

Is the HOI4 Agent Tools MCP server still maintained?

HOI4 Agent Tools is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the HOI4 Agent Tools MCP server under?

HOI4 Agent Tools 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 HOI4 Agent Tools MCP server?

VerifyMCP ran 15 checks on HOI4 Agent Tools, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about HOI4 Agent Tools: Malware scan. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.