OpenTelemetry MCP Server (Traceloop)
Query OpenTelemetry traces from Jaeger, Tempo or Traceloop backends.
By defaultRead-only
With our presetSame: read-only is built in
Labels are provisional (from the project README/docs, checked Oct 27, 2026). Not yet tested in our sandbox.
Read-only switch
Trace query tools only.
Preset
Read-onlyThe docs say it only reads, so there's no flag to add. Not sandbox-tested yet.
- Matched by name only. OpenTelemetry MCP Server (Traceloop) is documented as read-only, but a fork or another server with the same name might not be. So Codex still prompts and Claude Code asks.
Claude Code
.mcp.json
{
"mcpServers": {
"opentelemetry": {
"command": "pipx",
"args": ["run", "opentelemetry-mcp"]
}
}
}.claude/settings.json
{
"permissions": {
"ask": ["mcp__opentelemetry"]
}
}ask makes Claude Code prompt before every tool from this server.
Codex
~/.codex/config.toml
# Generated by redpresets.dev on 2026-11-03. Unverified preset. Also use a read-only credential. Not a security guarantee.
[mcp_servers.opentelemetry]
command = "pipx"
args = ["run", "opentelemetry-mcp"]
default_tools_approval_mode = "prompt"default_tools_approval_mode = "prompt" asks before every tool call.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"opentelemetry": {
"type": "stdio",
"command": "pipx",
"args": ["run", "opentelemetry-mcp"]
}
}
}Don't add write tools to mcpAllowlist in .cursor/permissions.json. Leave them on approval. Cursor's docs say the allowlist is not a security boundary.
Credential layer
Point at a query-only backend endpoint.
Facts
- Vendor
- Traceloop
- License
- Apache-2.0
- GitHub stars
- 204
- Latest release
- 0.2.2 (Feb 8, 2026)
- Last push
- Jun 21, 2026
- Status
- Active
- Last checked
- Oct 27, 2026
Sources
- README · checked Oct 27, 2026
Spotted something wrong? Labels change when vendors change. Suggest a correction