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.x51xxx/codex-mcp-tool

NPM · @TRISHCHUK/CODEX-MCP-TOOL · SCANNED AUG 3

MCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review

+16 this week 66 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 (95 of 99), 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 (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability66
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Context-footprint check failed: tool/resource definitions use about 2333 tokens (~179/item across 13 items; 13 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 Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
  • 92% of tools have a non-trivial description (not blank, and not just the tool's name).Partial
  • 99% of tool parameters carry a description.Partial
  • Structured output schemas are declared (46% of tools); any adoption earns full credit.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 · @trishchuk/codex-mcp-tool

# add to Claude Code
claude mcp add x51xxx-codex-mcp-tool -- npx -y @trishchuk/codex-mcp-tool
# add to Codex CLI
codex mcp add x51xxx-codex-mcp-tool -- npx -y @trishchuk/codex-mcp-tool
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "x51xxx-codex-mcp-tool": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@trishchuk/codex-mcp-tool"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add x51xxx-codex-mcp-tool --command npx --arg -y --arg @trishchuk/codex-mcp-tool
# ~/.hermes/config.yaml
mcp_servers:
  x51xxx-codex-mcp-tool:
    command: "npx"
    args: ["-y", "@trishchuk/codex-mcp-tool"]
// mcp.json
{
  "mcpServers": {
    "x51xxx-codex-mcp-tool": {
      "command": "npx",
      "args": [
        "-y",
        "@trishchuk/codex-mcp-tool"
      ]
    }
  }
}
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.

  • 3 Aug 26 +3
    • Stability: unverified → 0.23 functional
  • 2 Aug 26 +58
    • Provenance: unverified → fail security
    • Known CVEs: unverified → partial security
    • Install scripts: unverified → pass security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Security disclosure: fail → unverified functional
    • License: unverified → pass functional
    • Schema quality: unverified → fair functional
    • Tool coverage: unverified → 92 functional
    • Schema quality: unverified → 100 functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Licence: MIT functional
  • 1 Aug 26 −19
    • Tool coverage: 92 → unverified functional
    • Schema quality: 100 → unverified functional
  • 31 Jul 26 −8
    • 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 50

    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/@trishchuk/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

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

MCP tools — 13 exposed · ~2,333 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
ask-codex ~860

Execute Codex CLI with file analysis (@syntax), skills ($syntax), model selection, and safety controls. Supports changeMode.

NameTypeReqDescription
addDirsarrayAdditional writable directories beyond workspace (e.g., ["/tmp", "/var/log"]). Useful for monorepos and multi-directory projects.
approvalstringApproval policy: untrusted, on-failure, on-request, never
approvalPolicystringApproval: never, on-request, on-failure, untrusted
cdstringWorking directory
changeModebooleanReturn structured OLD/NEW edits for refactoring
chunkCacheKeystringCache key for continuation
chunkIndexnumberChunk index (1-based)
configConfiguration overrides as 'key=value' string or object
disableFeaturesarrayDisable feature flags (repeatable). Equivalent to -c features.<name>=false
enableFeaturesarrayEnable feature flags (repeatable). Equivalent to -c features.<name>=true
fullAutobooleanFull automation mode
imageOptional image file path(s) to include with the prompt
includeMetadatabooleanInclude configuration metadata in response
includeThinkingbooleanInclude reasoning/thinking section in response
localProviderstringSpecify which local provider to use (lmstudio or ollama). Automatically enables --oss if not set. If omitted with --oss, uses config default or shows selection.
modelstringModel: gpt-5.4, gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2. Default: gpt-5.4
ossbooleanUse local Ollama server (convenience for -c model_provider=oss). Requires Ollama running locally. Automatically sets sandbox to workspace-write if not specified.
outputLastMessagestringWrite final Codex message to file path. Useful for CI/CD result capture (Codex CLI v0.95.0+)
outputSchemaJSON Schema path or inline schema to constrain output format (Codex CLI v0.95.0+)
personalitystringCommunication style: pragmatic (concise, machine-friendly) or friendly (conversational). Codex CLI v0.94.0+
profilestringConfiguration profile to use from ~/.codex/config.toml
promptstringyesTask or question. Use @ to include files (e.g., '@largefile.ts explain').
reasoningEffortstringReasoning depth level: low (fast), medium (default), high (complex), xhigh (extra deep)
resetSessionbooleanClear session context before execution. Starts fresh conversation.
responseModestringResponse verbosity: "clean" returns only the final answer (default), "full" returns the complete execution log including thinking, tool calls, and agent activity
sandboxbooleanQuick automation mode: enables workspace-write + on-failure approval. Alias for fullAuto.
sandboxModestringAccess: read-only, workspace-write, danger-full-access
searchbooleanEnable web search using native --search flag (v0.52.0+). Requires network access - automatically sets sandbox to workspace-write if not specified.
sessionIdstringSession ID for conversation continuity. Enables native Codex resume.
skipGitRepoCheckbooleanSkip git repository validation. Useful for non-git directories (Codex CLI v0.75.0+)
timeoutnumberMaximum execution time in milliseconds (optional)
toolOutputTokenLimitnumberMaximum tokens for tool outputs (100-10,000). Controls response verbosity.
workingDirstringWorking directory for execution
yoloboolean⚠️ Bypass all safety (dangerous)

No output schema declared.

No examples provided.

batch-codex ~244

Delegate multiple atomic tasks to Codex for batch processing. Ideal for repetitive operations, mass refactoring, and automated code transformations

NameTypeReqDescription
disableFeaturesarrayDisable feature flags
enableFeaturesarrayEnable feature flags
modelstringModel to use: gpt-5.4, gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2
ossbooleanUse local Ollama server
parallelbooleanExecute tasks in parallel (experimental)
sandboxstringSandbox mode: read-only, workspace-write, danger-full-access
searchbooleanEnable web search for all tasks (activates web_search_request feature)
stopOnErrorbooleanStop execution if any task fails
tasksarrayyesArray of atomic tasks to delegate to Codex
timeoutnumberMaximum execution time per task in milliseconds
workingDirstringWorking directory for execution
NameTypeReqDescription
failednumberyes
resultsarrayyes
skippednumberyes
successfulnumberyes
totalnumberyes

No examples provided.

brainstorm ~444

Generate creative ideas using structured frameworks with domain context and feasibility analysis.

NameTypeReqDescription
approvalPolicystringApproval: never, on-request, on-failure, untrusted
cdstringWorking directory
constraintsstringLimitations: budget, time, technical, legal, etc.
disableFeaturesarrayDisable feature flags
domainstringDomain: software, business, creative, research, product, marketing, etc.
enableFeaturesarrayEnable feature flags
existingContextstringBackground info or previous attempts
fullAutobooleanFull automation mode
ideaCountintegerNumber of ideas (default: 12, range: 5-30)
includeAnalysisbooleanInclude feasibility/impact analysis
localProviderstringSpecify which local provider to use (lmstudio or ollama). Automatically enables --oss if not set.
methodologystringFramework: divergent, convergent, scamper, design-thinking, lateral, auto (default)
modelstringModel: gpt-5.4, gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2. Default: gpt-5.4
ossbooleanUse local Ollama server
personalitystringCommunication style: pragmatic (concise, machine-friendly) or friendly (conversational). Codex CLI v0.94.0+
promptstringyesBrainstorming challenge or question
reasoningEffortstringReasoning depth: low (fast), medium (default), high (complex), xhigh (extra deep)
sandboxModestringAccess: read-only, workspace-write, danger-full-access
searchbooleanEnable web search for research (activates web_search_request feature)
yoloboolean⚠️ Bypass all safety (dangerous)

No output schema declared.

No examples provided.

do-act ~253

Execute task via Codex, verify with shell command, auto-fix on failure. Act-Check-Fix loop.

NameTypeReqDescription
fullAutobooleanFull automation mode
localProviderstring
maxRetriesintegerMax retry attempts if verify fails. Default: 2
modelstringModel: gpt-5.4, gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2. Default: gpt-5.4
ossbooleanUse local Ollama/LM Studio
reasoningEffortstringReasoning depth
sandboxModestringAccess: read-only, workspace-write, danger-full-access
taskstringyesTask for Codex to execute
timeoutnumberCodex timeout per attempt in ms. Default: 10min
verifyobjectShell command to validate result. Triggers act-check-fix loop on failure.
workingDirstringWorking directory
NameTypeReqDescription
attemptsnumberyes
durationMsnumberyes
statusstringyes
stepsarrayyes

No examples provided.

fetch-chunk ~66

Retrieves cached chunks from a changeMode response. Use this to get subsequent chunks after receiving a partial changeMode response.

NameTypeReqDescription
cacheKeystringyesThe cache key provided in the initial changeMode response
chunkIndexnumberyesWhich chunk to retrieve (1-based index)

No output schema declared.

No examples provided.

health ~43

Check Codex CLI and session health status

NameTypeReqDescription
sessionIdstringOptional session ID to check specific session health
verbosebooleanInclude detailed diagnostic information
NameTypeReqDescription
codexCliobjectyes
featuresobjectyes
issuesarrayyes
sessionsobjectyes
statusstringyes

No examples provided.

Help ~11

receive help information

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list-sessions ~56

List all active conversation sessions with metadata, or manage sessions

NameTypeReqDescription
actionstringAction: list (default), delete (single session), clear (all sessions)
sessionIdstringSession ID for delete action
NameTypeReqDescription
actionstringyes
sessionsarray
statsobject

No examples provided.

list-skills ~42

Discover available Codex skills from .agents/skills/ directory

NameTypeReqDescription
workingDirstringWorking directory to search for skills. Defaults to resolved working directory.
NameTypeReqDescription
baseDirstringyes
skillsarrayyes

No examples provided.

ping ~19

Echo

NameTypeReqDescription
promptstringMessage to echo

No output schema declared.

No examples provided.

review-changes ~249

Run a code review against the current repository using Codex CLI native review subcommand

NameTypeReqDescription
basestringReview changes against a specific base branch (e.g., "main", "develop")
commitstringReview the changes introduced by a specific commit SHA
modelstringModel: gpt-5.4, gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5.2. Default: uses Codex's default
promptstringCustom review instructions or focus areas (cannot be used with uncommitted=true; use base/commit review instead)
timeoutnumberMaximum execution time in milliseconds
titlestringOptional title to display in the review summary
uncommittedbooleanReview staged, unstaged, and untracked changes (working tree) - cannot be combined with custom prompt
workingDirstringWorking directory to run the review in (passed via -C as a global Codex option)

No output schema declared.

No examples provided.

timeout-test ~33

Test timeout prevention by running for a specified duration

NameTypeReqDescription
durationnumberyesDuration in milliseconds (minimum 10ms)

No output schema declared.

No examples provided.

version ~13

Display version and system information

Input schema present but exposes no named parameters.

NameTypeReqDescription
codexClistring
mcpServerstringyes
nodeJsstringyes
platformstringyes

No examples provided.