部分failed to start: request timed out 可以通过添加来解决
startup_timeout_ms = 20000
完整示例如下
[mcp_servers.duckduckgo-search]
type = "stdio"
command = "uvx"
args = [ "duckduckgo-mcp-server" ]
startup_timeout_ms = 20000
设置uv镜像也可以解决部分uvx的mcp问题
echo 'export UV_DEFAULT_INDEX="https://pypi.tuna.tsinghua.edu.cn/simple"'>> ~/.bashrc
source ~/.bashrc
其中serena可能会一直提示超时,按照github仓库readme的操作,codex中对话输入 Activate the current dir as project using serena
输入一次之后就不会再显示超时了
Codex will often show the tools as failed
even though they are successfully executed. This is not a problem, seems to be a bug in Codex. Despite the error message, everything works as expected.
Codex 通常会将工具显示为 失败
,即使它们已成功执行。这不是问题,似乎是 Codex 中的一个错误。尽管有错误消息,但一切都按预期进行。
实测可用的MCP配置文件如下,加到 ~/.codex/config.toml
后面即可
[mcp_servers.context7]
command = "npx"
args = ["-y", "@upstash/context7-mcp"]
[mcp_servers.mcp-deepwiki]
command = "npx"
args = ["-y", "mcp-deepwiki@latest"]
[mcp_servers.spec-workflow]
command = "npx"
args = ["-y", "@pimzino/spec-workflow-mcp@latest"]
[mcp_servers.sequential-thinking]
command = "npx"
args = ["-y", "@modelcontextprotocol/server-sequential-thinking"]
[mcp_servers.serena]
command = "uvx"
args = ["--from", "git+https://github.com/oraios/serena", "serena", "start-mcp-server"]
startup_timeout_ms = 20000
[mcp_servers.duckduckgo-search]
type = "stdio"
command = "uvx"
args = [ "duckduckgo-mcp-server" ]
startup_timeout_ms = 20000