mcp-server-codex

A Model Context Protocol (MCP) server package intended to provide tools/resources to AI agents (e.g., for Codex-like coding assistance).

Evaluated Apr 04, 2026 (27d ago)
Homepage ↗ Repo ↗ DevTools mcp ai-agents developer-tools coding-assistance integration
⚙ Agent Friendliness
33
/ 100
Can an agent use this?
🔒 Security
36
/ 100
Is it safe for agents?
⚡ Reliability
18
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
45
Documentation
35
Error Messages
0
Auth Simplicity
30
Rate Limits
0

🔒 Security

TLS Enforcement
60
Auth Strength
25
Scope Granularity
20
Dep. Hygiene
40
Secret Handling
40

No concrete security or operational details (TLS requirements, auth mechanism, secret handling, logging/redaction, allowed tool scopes) were provided in the supplied data, so scores reflect uncertainty rather than verified strength.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
20
Error Recovery
20
AF Security Reliability

Use Cases

  • Connecting an MCP-capable agent to coding/helpful tools exposed by the MCP server
  • Automating code-related workflows via agent tool calls
  • Providing a standardized interface for integrating coding assistance into agent environments

Not For

  • Direct human-facing use without an MCP-capable client
  • Production environments requiring strong, explicitly documented security/auth guarantees from this package alone (based on available info)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication details were provided in the supplied data, so auth strength/requirements could not be verified.

Pricing

Free tier: No
Requires CC: No

No pricing information was provided.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • MCP tool-call contracts (inputs/outputs) may be underspecified depending on the implementation
  • Agents may unintentionally pass large/unbounded inputs if size limits are not documented
  • If tool actions are not idempotent (e.g., file writes), agents may repeat operations on retries

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-server-codex.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered