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.

io.github.ChiR24/unreal-engine-mcp

NPM · UNREAL-ENGINE-MCP-SERVER · SCANNED SEP 20

MCP server for Unreal Engine 5 with 23 tools for game development automation.

−7 this week 67 Trust /100
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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 98 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1340 tokens (~111/item across 12 items; 1 tools + 11 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 Management0
  • Stability check failed: the tool surface changed between 0.5.30 and 0.6.0-beta-a: 23 tool removals, 0 breaking changes, 1 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
  • 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 1 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 3 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
Install

How do I install the io.github.ChiR24/unreal-engine-mcp server?

io.github.ChiR24/unreal-engine-mcp runs locally as an npm package, launched with npx -y unreal-engine-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · unreal-engine-mcp-server

# add to Claude Code
claude mcp add chir24-unreal-engine-mcp -- npx -y unreal-engine-mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "chir24-unreal-engine-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "unreal-engine-mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "chir24-unreal-engine-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "unreal-engine-mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add chir24-unreal-engine-mcp -- npx -y unreal-engine-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "chir24-unreal-engine-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "unreal-engine-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add chir24-unreal-engine-mcp --command npx --arg -y --arg unreal-engine-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  chir24-unreal-engine-mcp:
    command: "npx"
    args: ["-y", "unreal-engine-mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "chir24-unreal-engine-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "unreal-engine-mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add chir24-unreal-engine-mcp -t stdio -c npx -a -y unreal-engine-mcp-server
// mcp.json
{
  "mcpServers": {
    "chir24-unreal-engine-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "unreal-engine-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.

  • 19 Sept 26 +15
    • Malware scan: unverified → pass security
  • 18 Sept 26 −20
    • Malware scan: pass → unverified security
    • Stability: 0.80 → fail security
    • Security disclosure: unverified → fail functional
    • Tool coverage: 60% → 100% functional
    • Schema quality: 854 → 111 functional
    • First check of Tool coverage: 100 functional
    • Schema quality: fair → excellent functional
    • Package version: 0.5.30 → 0.6.0-beta-a functional
  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
    • Security disclosure: fail → unverified functional
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −3
    • Stability: pass → 0.77 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 20 Sept 2026 · Analysed npm/unreal-engine-mcp-server@0.6.0-beta-a

Provenance No attestation

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

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 98 packages
Packages resolved 98
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 1 exposed · ~765 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
unreal ~765

Unreal Engine editor automation: one tool, four operations. Always in this order: (1) search with query = 2-4 plain words naming the verb and the object, e.g. 'spawn actor', 'add variable blueprint', 'save level'; every result row carries a one-line summary, its effect and a ready-made nextCall. (2) describe: send the chosen row's nextCall unchanged; the reply is the exact contract: parameters (name, type, required), inputSchema, a working example and, when required, consentGrant. (3) execute: send describe's nextCall with params filled in, using ONLY the parameter names describe listed. Rules: never guess capability ids, tool names, action names or parameter names; never put action or subAction inside params; a failed call returns suggestions and an executable nextCall, so send that nextCall instead of retrying blindly. To browse instead of search, call describe with no selector and follow the nextCall on each row one level down. configure only enables or disables internal tool groups; it never performs editor work.

NameTypeReqDescription
actionstringExact action name copied from a search row or describe response. For configure, this is a manage_tools action.
capabilitystringExact canonical capability id (or declared alias) copied from a search row or describe response, e.g. blueprint.create. Preferred selector for describe and execute; never guessed.
consentobjectPer-call consent grant for a capability whose policy.consent is not 'none'. Bound to one capability and one call; never persisted, inherited or reused. Read the exact grant from describe.consentGrant…
cursorstringOpaque search cursor from a previous response nextCursor. Supersedes offset.
domainstringCapability domain to browse or filter by. Call describe with no selector to list domains.
effectstringFilter search results by declared behavior effect.
familystringCapability family inside a domain. Call describe with a domain to list its families.
limitintegerMaximum rows per page: search results (default 12) or describe action rows (default 20). Defaults to 12.
maxBytesintegerSerialized byte ceiling for a search response. Results are dropped from the end until the response fits.
offsetintegerZero-based offset into search results or into a described tool's action list. Defaults to 0.
operationstringyessearch finds capabilities by plain words. describe returns one capability's exact contract, or browses one level when given no selector. execute runs one validated action. configure enables or disabl…
optionsobjectExecution controls for execute only; never put these inside params. Honored keys: idempotencyKey, expectedCatalogRevision, expectedRevisions, timeoutMs.
paramstringExact parameter name to inspect on one capability. Use with describe plus tool and action; returns that single parameter's schema plus the consent grant, when the capability needs one.
paramsobjectParameters for execute or configure: an object whose keys are exactly the parameter names describe listed for this action, with the same casing. Never include action or subAction here.
querystring2-4 plain words naming the verb and the object, e.g. 'spawn actor', 'add variable blueprint', 'save level'. Matched against action names, topics, family, domain and summary; full sentences and filler…
toolstringExact parent tool name copied from a search row (parentTool) or a describe response. Always paired with action; never guessed.
NameTypeReqDescription
actionstring
actionCountinteger
actionHasMoreboolean
actionLimitinteger
actionOffsetinteger
actionsarrayPaginated/filterable action list on tool-only describe.
availabilityWhether the capability is available, disabled or unavailable, and why.
availableActionsarray
availableParametersarray
behaviorobject
browseobjectOn a tool-only describe: a search call filtered to that tool, whose rows carry per-action summaries.
capabilitiesarrayBounded capability list on a family-level describe.
capabilitystringCanonical capability ID this response describes.
catalogRevisionstringRevision of the generated canonical capability catalog this response was served from.
consentGrantobjectExact consent grant this capability requires, ready to pass back as the execute call's consent sibling. Absent when policy.consent is 'none'.
costobject
dataExecute payload projected against the capability's declared output schema. Bound to receipt.dataDigest, and the same location the native /mcp surface publishes.
deprecationobject
domainstring
domainsarrayBounded domain list on a catalog-level describe.
drillDownobjectExample nextCall payload to drill one level deeper.
errorstring
errorCodestring
familiesarrayBounded family list on a domain-level describe.
familystring
filtersobjectFilters applied to this search.
hasMoreboolean
hashesobjectPer-record schema and content hashes from the generated catalog.
inputSchemaobjectExact input schema of the described capability. Never a parent-tool union.
limitinteger
maxBytesinteger
messagestring
migratedFromobjectLegacy tool/action pair that resolved to this capability.
nextCallobjectDirectly-invokable gateway request for guided self-correction.
nextCursorstringCursor to pass back as cursor to continue a search.
offsetinteger
operationstringyes
outputSchemaobjectExact output schema of the described capability.
outputsarray
paramstring
parameterCountinteger
parameterHasMoreboolean
parameterLimitinteger
parameterOffsetinteger
parametersarrayPaginated/filterable compact parameter catalog on tool+action describe.
parentToolstringLegacy parent tool that dispatches the described capability.
perActionSchemasboolean
policyobject
reasonsarray
requiredbooleanWhether the described param is required.
resolvedFromAliasstringDeclared alias that resolved to this capability.
result
resultsarray
runnablebooleanFalse when the capability cannot currently be executed; nextCall then points at the fix.
schemaobjectFull schema of the single described param.
scopestringCatalog scope: 'tool' for a tool summary, 'union' for the tool-union parameter catalog.
successbooleanyes
suggestionsarrayClosest-match names for an invalid tool/action/param call.
toolstring
totalinteger
truncatedbooleanTrue when results were dropped to fit the byte budget.

No examples provided.

Common questions

What is the io.github.ChiR24/unreal-engine-mcp server?

io.github.ChiR24/unreal-engine-mcp is listed in the public MCP registry as io.github.ChiR24/unreal-engine-mcp. MCP server for Unreal Engine 5 with 23 tools for game development automation. This page covers its npm package (unreal-engine-mcp-server).

Is the io.github.ChiR24/unreal-engine-mcp server safe to use?

io.github.ChiR24/unreal-engine-mcp scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 io.github.ChiR24/unreal-engine-mcp server expose?

io.github.ChiR24/unreal-engine-mcp exposes 1 tool: unreal. Their descriptions and schemas cost roughly 765 tokens of context every time the server is loaded.

Is the io.github.ChiR24/unreal-engine-mcp server still maintained?

io.github.ChiR24/unreal-engine-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 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 io.github.ChiR24/unreal-engine-mcp server under?

io.github.ChiR24/unreal-engine-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.