Surfaces Ollama gen_ai.* LLM spans and supports local Ollama/OpenAI-compatible models for slow-trace diagnosis.
Surfaces OpenAI gen_ai.* LLM spans in trace inspection, enabling analysis of OpenAI LLM calls alongside other spans.
Acts as a local OpenTelemetry collector for OTLP/JSON traces, rendering terminal flamegraphs and exposing trace inspection, critical path, SQL N+1, and gen_ai metrics through MCP tools.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
One command local OpenTelemetry collector: npx otel-pocket (or bunx otel-pocket) listens on :4318 for OTLP/JSON traces, renders a live terminal flamegraph, flags SQL N+1 loops, and surfaces gen_ai.* LLM spans (Ollama, OpenAI, Anthropic).
bunx otel-pocket
npx otel-pocket
# or install in your project / globally
bun add -d otel-pocket
npm i -D otel-pocketJSR:
bunx jsr add @kanchingyg/otel-pocket
npx jsr add @kanchingyg/otel-pocketgo install github.com/kanchingyg/otel-pocket@latestThe core collector runs in Go (main.go, internal/). TypeScript under src/*.ts is included for npx / bunx / JSR usage and MCP bridge helpers.
Related MCP server: tracehub-mcp
npx otel-pocket
bunx otel-pocket
# point your SDK exporter to http://127.0.0.1:4318/v1/tracesnpx otel-pocket --mcpAdd to Cursor or Claude Code MCP config:
{
"mcpServers": {
"otel-pocket": {
"command": "npx",
"args": ["-y", "otel-pocket", "--mcp"]
}
}
}Tool | Purpose |
| Recent traces with duration and error status |
| Span tree, critical path, N+1 SQL, and |
| Ask a local OpenAI-compatible model (Ollama/LM Studio); loopback-only unless |
Set OTEL_POCKET_LLM_URL / OTEL_POCKET_LLM_MODEL for local LLM diagnosis.
Jaeger and desktop viewers require a browser, lack a terminal TUI, and do not ship MCP tools for coding agents. Phoenix and Langfuse are heavy Python/Docker stacks. otel-pocket correlates HTTP, SQL N+1, and gen_ai.* spans in a single zero-config npx, bunx, or go install binary.
Tool | Mutates | Description |
|
| List recent OTLP traces stored in memory with total duration, span count, and error status. |
|
| Render the hierarchical span tree, critical path, collapsed SQL N+1 loops, and |
|
| Send a sanitized trace summary to a loopback Ollama or OpenAI-compatible model for bottleneck analysis. |
.cursor/mcp.json){
"mcpServers": {
"otel-pocket": {
"command": "npx",
"args": ["-y", "otel-pocket", "--mcp"]
}
}
}claude mcp add otel-pocket -- npx -y otel-pocket --mcpimport * as bridge from "jsr:@kanchingyg/otel-pocket/bridge";Stdio frame isolation: When --mcp is active, hijackStdoutForMcp() redirects accidental console.log calls to stderr so JSON-RPC 2.0 frames on stdout never corrupt.
Read-only by default: Mutating tools (mutates: true) are blocked in --dry-run mode and require explicit --allow-write authorization.
Loop breaker: Repeated identical (toolName, args) invocations are hashed with SHA-256 and halted after 3 consecutive repeats to prevent runaway agent loops.
Context budget truncation: Tool outputs are middle-truncated (60% head / 40% tail) scaled to the probed local model n_ctx (Ollama /api/show, llama.cpp /props, vLLM /v1/models).
Secret redaction and path normalization: AWS keys (AKIA*, ASIA*), bearer tokens, and sk-* keys are scrubbed before returning tool output, and Windows drive paths (C:\...) translate cleanly to /mnt/c/... when WSL mode is enabled.
This server cannot be deployed
LLM Orchestration Agent (Opentelemetry Api)
AI agent observability for production traces, natural-language insights, and improvement loops.
Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
LLM Orchestration Agent (Opentelemetry Instrumentation Fastapi)
