Agent skill

Frontmcp Observability

by agentfront in agentfront/frontmcp

A skill your agent uses when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server.

Apache-2.0Auto-check passedDevOps & Cloud

Install Frontmcp Observability

skills CLI
$ npx skills add agentfront/frontmcp --skill frontmcp-observability -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agentfront/frontmcp frontmcp-observability --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agentfront/frontmcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/libs/skills/catalog/frontmcp-observability .claude/skills/frontmcp-observability && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
frontmcp-observability
GitHub stars
146
Token cost
~4.6k tokens
SKILL.md length
1,132 words
Files
20 (incl. references)
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server.

  • Works in 3 steps: Choose What You Need → Enable Observability → Read the Relevant Reference
  • Structured logging
  • SKILL.md covers When to Use This Skill, Prerequisites, Step 1: Choose What You Need and Step 2: Enable Observability, plus 9 more sections
  • Calls npm

What it does

Frontmcp Observability is an agent skill from agentfront/frontmcp. Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and configurable sinks (Winston, Pino, stdout); the off-by-default /metrics endpoint (process and framework metrics, Prometheus-compatible); vendor integrations (Coralogix, Datadog, Logz.io, Grafana Cloud…

Its SKILL.md is about 4.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 26 other files, including reference files (for example `examples/metrics-endpoint/enable-metrics-endpoint.md`, `examples/structured-logging/stdout-logging.md` and `examples/structured-logging/winston-integration.md`).

It sits in DevOps & Cloud, covering Observability and Monitoring and alerting. It works with OpenTelemetry, Datadog, Grafana and Prometheus. The repository describes itself as: TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow. The licence is Apache-2.0.

When your agent uses it

  • Structured logging
  • Monitoring to a FrontMCP server

Example prompts

  • “/frontmcp-observability”

Requirements

  • Node.js

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Choose What You Need
  2. Enable Observability
  3. Read the Relevant Reference

What it can do on your machine

Read from SKILL.md and the folder at commit 8f59ba8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.agentfront.dev

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Frontmcp Observability loads about 4.6k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 197 tokens; SKILL.md has 1,132 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~197
When it runs · the whole SKILL.md, loaded when a task matches
~4.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from agentfront/frontmcp at commit 8f59ba8, republished under its Apache-2.0 licence (© agentfront). 1,132 words, ~4,594 tokens.

Download SKILL.mdSave it as .claude/skills/frontmcp-observability/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.
name
frontmcp-observability
description
Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and configurable sinks (Winston, Pino, stdout); the off-by-default /metrics endpoint (process and framework metrics, Prometheus-compatible); vendor integrations (Coralogix, Datadog, Logz.io, Grafana Cloud, or any OTLP backend); and testing spans, log correlation, and instrumentation. Triggers: observability, telemetry, tracing, logging, monitoring, OpenTelemetry, OTel, spans, metrics, Prometheus, Datadog, Coralogix, Logz.io, Grafana, Winston, Pino.
tags
router, observability, telemetry, tracing, logging, monitoring, opentelemetry, otel, spans
category
observability
targets
all
bundle
recommended, full
priority
10
visibility
both
license
Apache-2.0
metadata.docs
https://docs.agentfront.dev/frontmcp/guides/observability

FrontMCP Observability

Router for adding observability to FrontMCP servers. Covers distributed tracing (OpenTelemetry), structured JSON logging, per-request log collection, the this.telemetry developer API, and vendor integrations.

When to Use This Skill

Must Use
  • Adding tracing, logging, or monitoring to a FrontMCP server
  • Connecting Coralogix, Datadog, Logz.io, Grafana, or any OTLP backend
  • Using this.telemetry to create custom spans in tools, plugins, or agents
  • Setting up structured logging with winston, pino, or NDJSON stdout
  • Testing that spans and log entries are created correctly
  • Before going to production (see also frontmcp-production-readiness)
  • When debugging request latency or error rates
  • When building plugins that need trace context propagation
Skip When
  • Building a prototype that doesn't need observability yet
  • Configuring auth, transport, or throttle (see frontmcp-config)
  • Setting up the project from scratch (see frontmcp-setup)

Decision: Use this skill when you need to observe, trace, or log your server. Start with tracing-setup for auto-instrumentation, add structured-logging for production logs, and use telemetry-api for custom spans in your code.

Prerequisites

  • A working FrontMCP server (see frontmcp-setup)
  • npm install @frontmcp/observability

Step 1: Choose What You Need

I want to...Reference
Enable auto-tracing for all flowsreferences/tracing-setup.md
Add structured JSON logging with trace correlationreferences/structured-logging.md
Create custom spans in tools/pluginsreferences/telemetry-api.md
Connect Coralogix, Datadog, Logz.io, Grafanareferences/vendor-integrations.md
Test that spans and logs are correctreferences/testing-observability.md
Expose Prometheus /metrics endpointreferences/metrics-endpoint.md

Step 2: Enable Observability

The simplest way — one config line:

typescript
@FrontMcp({
  observability: true,
})

This enables auto-tracing for all SDK flows. Add structured logging:

typescript
@FrontMcp({
  observability: {
    tracing: true,
    logging: { sinks: [{ type: 'stdout' }] },
    requestLogs: true,
  },
})

Step 3: Read the Relevant Reference

Follow the scenario routing table above to find the right reference for your use case.

Scenario Routing Table

ScenarioReferenceDescription
Enable OpenTelemetry tracingreferences/tracing-setup.mdZero-config auto-instrumentation, setupOTel(), span hierarchy
Add JSON logs with trace correlationreferences/structured-logging.mdSinks (stdout, console, OTLP, winston, pino), redaction, log format
Custom spans in tools/pluginsreferences/telemetry-api.mdthis.telemetry.startSpan(), withSpan(), addEvent(), setAttributes()
Connect to monitoring platformsreferences/vendor-integrations.mdCoralogix, Datadog, Logz.io, Grafana — OTLP and direct
Test spans and log entriesreferences/testing-observability.mdcreateTestTracer(), assertSpanExists(), integration test patterns
Expose Prometheus /metrics endpointreferences/metrics-endpoint.mdOff-by-default Prometheus scrape endpoint with process + framework counters

Common Patterns

PatternCorrectIncorrectWhy
Enable observabilityobservability: true in @FrontMcp configImport and install ObservabilityPlugin manuallyConfig-driven is the standard pattern since v1.0
Custom spansthis.telemetry.withSpan('op', fn)trace.getTracer().startSpan() directlythis.telemetry auto-inherits trace context
Log correlationthis.logger.info('msg', { key: val })console.log('msg')SDK logger flows through StructuredLogTransport with trace_id
Session IDUse mcp.session.id attribute (hashed)Log the real session IDPrivacy: the hash is sufficient for correlation
Vendor integrationUse { type: 'otlp', endpoint } sinkBuild vendor-specific HTTP clientsOTLP is the universal standard

Quick Reference: What Gets Traced

CategoryFlowsAttributes
HTTP requeststraceRequest, auth, route, finalizehttp.request.method, url.path
Tool callsparseInput → findTool → execute → finalizemcp.component.type=tool, enduser.id
Resource readsparseInput → findResource → executemcp.component.type=resource, mcp.resource.uri
PromptsparseInput → findPrompt → executemcp.component.type=prompt
AgentsparseInput → findAgent → execute (nested tool calls)mcp.component.type=agent
Authverify, session verify, OAuth flowsfrontmcp.auth.mode, frontmcp.auth.result
TransportSSE, Streamable HTTP, Stateless HTTPfrontmcp.transport.type
Skillssearch, load, HTTP endpointsfrontmcp.flow.name

Verification Checklist

Configuration
  • @frontmcp/observability installed
  • observability field added to @FrontMcp config
  • TracerProvider configured (via setupOTel() or external SDK); the startup warning about a missing provider appears only when none is registered
  • Logging sinks configured for production (stdout or OTLP)
Runtime
  • Spans appear in trace backend when calling a tool
  • Log entries include trace_id and span_id
  • this.telemetry is available in tool execution contexts, and @frontmcp/observability is imported so it type-checks
  • Session tracing ID is consistent across all spans in a request
  • Errors are recorded on spans with ERROR status
Testing
  • Tests verify span creation with createTestTracer()
  • Tests verify log entries via CallbackSink
  • No test isolation issues (each test resets exporter)
Show full SKILL.md (538 more words)Show less

Troubleshooting

ProblemCauseSolution
this.telemetry is undefined in a toolobservability not enabled on the parent @FrontMcp configSet observability: true (or a config object) in the @FrontMcp decorator; see tracing-setup
Property 'telemetry' does not exist (TS2339)@frontmcp/observability is not part of the compilationAdd import type {} from '@frontmcp/observability' where you use it (or once in the server entry); see telemetry-api
Spans appear without trace_id in logsLogger not connected to StructuredLogTransportUse this.logger, not console; see structured-logging
OTLP exporter silently drops spansEndpoint URL points at the UI, not the OTLP collectorUse the OTLP HTTP/gRPC ingest endpoint exposed by your vendor (Datadog, Coralogix, Logz, etc.); see vendor-integrations
Real session ID appears in span attributesA custom span attribute writes session.id directlyUse the SDK-provided mcp.session.id (already hashed); never log the raw session token
Tests randomly fail with leftover spansExporter retained between testsReset the in-memory exporter in afterEach; see testing-observability
OTel auto-instrumentation double-traces requestsBoth setupOTel() AND a vendor agent attached to the processPick one: either FrontMCP-managed OTel OR the vendor agent — not both

Examples

Each reference has matching examples under examples/<reference>/:

tracing-setup
ExampleLevelDescription
basic-tracingBasicEnable auto-tracing and see spans printed to your terminal.
production-tracingIntermediateFull production observability — traces to OTLP, structured logs to stdout, per-request log collection.
structured-logging
ExampleLevelDescription
stdout-loggingBasicEnable NDJSON structured logging to stdout with automatic trace correlation and field redaction.
winston-integrationIntermediateForward FrontMCP structured log entries to your existing winston logger. Each entry includes trace_id and span_id as metadata.
telemetry-api
ExampleLevelDescription
tool-custom-spansBasicCreate child spans, events, and attributes inside a tool's execute method using this.telemetry.
plugin-telemetryIntermediateAdd telemetry events from a custom plugin's hooks. Events appear on the tool execution span, giving you visibility into plugin behavior within the trace.
agent-nested-tracingAdvancedTrace an agent's execution lifecycle including its nested tool calls. Every span shares the same trace ID.
vendor-integrations
ExampleLevelDescription
coralogix-setupIntermediateSend both traces and structured logs to Coralogix. Logs include trace_id so Coralogix links them to traces automatically.
testing-observability
ExampleLevelDescription
test-custom-spansBasicVerify that your tool creates the expected child spans with correct attributes.
test-log-correlationIntermediateVerify that structured log entries include trace context fields for correlation with spans.
metrics-endpoint
ExampleLevelDescription
enable-metrics-endpointBasicTurn on the /metrics endpoint with defaults and scrape it with curl.

Accessing This Skill

Skills are distributed as plain SKILL.md files plus a sibling references/ and examples/ tree, so consumers can pick whichever access mode fits:

ModeHow it works
FilesystemRead libs/skills/catalog/frontmcp-observability/ directly from a clone of the catalog repo, or from a published @frontmcp/skills install. SKILL.md is the entry point.
frontmcp CLIfrontmcp skills list, frontmcp skills read frontmcp-observability, frontmcp skills read frontmcp-observability:references/<file>.md, frontmcp skills install frontmcp-observability — no server required.
MCP skill://When a developer mounts this skill into their own FrontMCP server (@FrontMcp({ skills: [...] })), the SDK exposes it via SEP-2640 resources: skill://frontmcp-observability/SKILL.md, skill://frontmcp-observability/references/{file}.md, etc. The server’s skill://index.json returns the SEP-2640 discovery document for everything mounted on it.

The catalog itself is not an MCP server. The skill:// URIs only resolve when a server has been configured to host this skill.

Reference

© agentfront, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 19 other files (references) in libs/skills/catalog/frontmcp-observability of agentfront/frontmcp.

  • SKILL.md
  • examples/metrics-endpoint/enable-metrics-endpoint.md
  • examples/structured-logging/stdout-logging.md
  • examples/structured-logging/winston-integration.md
  • examples/telemetry-api/agent-nested-tracing.md
  • examples/telemetry-api/plugin-telemetry.md
  • examples/telemetry-api/skill-counters.md
  • examples/telemetry-api/tool-custom-spans.md
  • examples/testing-observability/test-custom-spans.md
  • examples/testing-observability/test-log-correlation.md
  • examples/tracing-setup/basic-tracing.md
  • examples/tracing-setup/production-tracing.md
  • examples/vendor-integrations/coralogix-setup.md
  • references
  • … and 6 more

Open the folder on GitHubat commit 8f59ba8

Compare with similar skills

Frontmcp Observability next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Frontmcp Observability compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Frontmcp Observability this skillagentfront/frontmcp146—~4.6kAutomated safety check: PassApache-2.0
Archestra Dev Observabilityarchestra-ai/archestra4.3k—~1.2kAutomated safety check: PassCustom licence
Monitoring Observabilityahmedasmar/devops-claude-skills203—~3.9kAutomated safety check: PassNone
ObservabilityTheBeardedBearSAS/claude-craft107—~547Automated safety check: PassMIT
Tsh Implementing ObservabilityTheSoftwareHouse/copilot-collections284—~2kAutomated safety check: PassMIT
Observability Architecturemajiayu000/litellm-rs116—~1.3kAutomated safety check: PassMIT

Similar skills

  • Archestra Dev Observability

    archestra-ai/archestra

    A skill your agent uses when changing Archestra tracing, metrics, OpenTelemetry, Tempo, Grafana, Prometheus, LLM/MCP spans, observability labels, or local observability setup.

    4.3k GitHub stars~1.2k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Monitoring Observability

    ahmedasmar/devops-claude-skills

    Monitoring and observability strategy, implementation, and troubleshooting.

    203 GitHub stars~3.9k tokensUpdated 5 mo ago
    DevOps & CloudAuto-check passed
  • Observability

    TheBeardedBearSAS/claude-craft

    OpenTelemetry, distributed tracing, structured logging, metrics (Prometheus, Grafana, Datadog).

    107 GitHub stars~547 tokensUpdated 23 days ago
    DevOps & CloudAuto-check passed
  • Tsh Implementing Observability

    TheSoftwareHouse/copilot-collections

    Observability patterns for logging, monitoring, alerting, and distributed tracing.

    284 GitHub stars~2k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed
  • Observability Architecture

    majiayu000/litellm-rs

    LiteLLM-RS Observability Architecture. An agent skill from majiayu000/litellm-rs.

    116 GitHub stars~1.3k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Monitoring Expert

    Jeffallan/claude-skills

    Sets up application monitoring: structured logs, Prometheus metrics, OpenTelemetry tracing, Grafana dashboards, alert rules and load tests with k6 or Artillery.

    12k GitHub stars~1.6k tokensUpdated 4 days ago
    DevOps & CloudAuto-check passed

More from agentfront/frontmcp

All 12 skills in this repo
  • Frontmcp Auth UI

    agentfront/frontmcp

    A skill your agent uses when customizing, branding, or replacing the built-in FrontMCP OAuth pages (the login, consent, federated-select, incremental-authorization, and error pages) with your own…

    146 GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Frontmcp Channels

    agentfront/frontmcp

    A skill your agent uses when pushing real-time notifications or events into Claude Code (or another MCP client) sessions, or building two-way chat bridges.

    146 GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Frontmcp Extensibility

    agentfront/frontmcp

    A skill your agent uses when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools.

    146 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Frontmcp Authorities

    agentfront/frontmcp

    A skill your agent uses when implementing authorization and access control for FrontMCP tools, resources, prompts, or skills, deciding who may invoke what.

    146 GitHub stars~7.1k tokensUpdated today
    Auto-check passed
  • Frontmcp Config

    agentfront/frontmcp

    A skill your agent uses when configuring a FrontMCP server through frontmcp.config or the @FrontMcp options.

    146 GitHub stars~7k tokensUpdated today
    Auto-check passed
  • Frontmcp Deployment

    agentfront/frontmcp

    A skill your agent uses when deploying, building for production, packaging, or shipping a FrontMCP server.

    146 GitHub stars~9.2k tokensUpdated today
    Auto-check: notes

Categories

Questions about Frontmcp Observability

What does Frontmcp Observability do?

A skill your agent uses when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Frontmcp Observability is an agent skill from agentfront/frontmcp. Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server.

When should I use Frontmcp Observability?

Frontmcp Observability fits situations like: structured logging; monitoring to a FrontMCP server.

How do I install Frontmcp Observability in Claude Code?

Run `npx skills add agentfront/frontmcp --skill frontmcp-observability -a claude-code`. Or copy the skill folder (libs/skills/catalog/frontmcp-observability in agentfront/frontmcp) into .claude/skills/frontmcp-observability in your project. Claude Code loads it when a task matches its description.

How do I install Frontmcp Observability in Codex?

Run `npx skills add agentfront/frontmcp --skill frontmcp-observability -a codex`. Or copy the skill folder (libs/skills/catalog/frontmcp-observability in agentfront/frontmcp) into .agents/skills/frontmcp-observability in your project. Codex loads it when a task matches its description.

Can I use Frontmcp Observability in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentfront/frontmcp --skill frontmcp-observability -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/frontmcp-observability, .gemini/skills/frontmcp-observability, .github/skills/frontmcp-observability and .opencode/skills/frontmcp-observability in your project.

What does Frontmcp Observability need to run?

Going by SKILL.md and its folder, Frontmcp Observability needs the command-line tools its instructions call (npm). Our summary lists: Node.js.

Does Frontmcp Observability access the network?

SKILL.md names 1 domain. As links in the text: docs.agentfront.dev. This is read from the text; nothing was executed.

Is Frontmcp Observability safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Frontmcp Observability use?

Frontmcp Observability is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Frontmcp Observability use?

About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Frontmcp Observability?

Skills that share tags, products or a category with Frontmcp Observability: Archestra Dev Observability (archestra-ai/archestra, 4.3k stars), Monitoring Observability (ahmedasmar/devops-claude-skills, 203 stars), Observability (TheBeardedBearSAS/claude-craft, 107 stars) and Tsh Implementing Observability (TheSoftwareHouse/copilot-collections, 284 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Frontmcp Observability?

agentfront (a GitHub organization) maintains it in agentfront/frontmcp, which has 146 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

Source: agentfront/frontmcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.