Flowlines

npx add-mcp 'https://api.flowlines.ai/mcp'

01 Who uses it

People, agents, accounts, workspaces, and clients when reported with permission.

02 What they want

Observed jobs and use cases, not a disconnected list of tool names.

03 Where it breaks

Loops, false success, corrections, abandonment, and missing outcomes.

04 What to do next

Evidence-backed signals for engineering, product, customer, and sales teams.

Calls 24,814 Sessions 844 Users & agents 286 Outcome coverage 93% Failed calls 1.2%

search_accounts 8,214 142 99.3%

enrich_company 5,108 119 98.8%

get_signals 4,812 97 97.9%

write_fields 2,264 61 94.2%

What call status misses

write_fields succeeds at the protocol layer, but 11 journeys leave requested fields unchanged.

Journey reconstruction

A successful tool call is not a successful journey.

Follow the use case from request to result. See the client, permitted identity, tool path, repeated calls, failures, outcome, and the sessions affected.

Themed sessions 748 Reported users 286 Use-case journeys 12 Loops to review 30

USE CASE search_accounts TOOL enrich_company TOOL get_signals OUTCOME Brief ready

7 repeated-call loops

Eight journeys ended without a reported outcome. Seven repeated the same signal lookup.

Layer	What it answers	Typical owner
Infrastructure	Is the service available, fast, and within capacity?	Platform and SRE
Tool calls	Which operation ran, failed, or called a dependency?	MCP engineering
Agent traces	What did one agent execution do?	AI engineering
Behavioral observability	What are users trying to do, what keeps failing, and who is affected?	Engineering, product, customer, sales
Outcome analytics	Did the complete job work, and what should change next?	Product and business

Flowlines complements Grafana, Datadog, Sentry, Honeycomb, Langfuse, LangSmith, and OpenTelemetry-compatible backends.

Engineering

Catch a recurring broken path.

Notify the owning team when agents repeat the same operation, recover badly from an error, or declare success without the needed result.

Example: 17 account-enrichment journeys looped after an empty lookup.

Product

See what users ask for next.

Group unsupported requests and manual workarounds by use case, user, and account before deciding what to build.

Example: 31 users asked the MCP to export a report it cannot create.

Customer

Find adoption risk before a ticket.

Spot an important account whose use of a new tool stalls, drops, or repeatedly ends without a measurable outcome.

Example: A pilot account tried the same setup journey seven times.

Commercial

Review meaningful buying signals.

Surface repeated security, deployment, integration, or scale questions in the right account context. A person decides whether to follow up.

Example: An enterprise account asked about private deployment in four sessions.

Examples are synthetic. Signals are leads for review, not automatic proof of cause or intent.

01

See the use case

Understand the real jobs people and agents give the server.

02

Follow the journey

See typical paths, loops, failures, and reported outcomes.

03

Find the people

Know which permitted users, accounts, agents, and clients drive the behavior.

04

Open the evidence

Inspect the relevant request and calls before deciding what changed.

01 / Category guide

MCP observability in production

Build the complete monitoring model across infrastructure, tools, sessions, behavior, and outcomes.

Read the guide › 02 / Product analytics

What users do with your MCP

Measure adoption, use cases, journeys, unmet needs, feedback, and commercial signals.

Read the guide › 03 / Buyer's guide

The best MCP observability tools

Compare behavioral analytics, APM, tracing, error tracking, and open-source options fairly.

Read the guide › 04 / Decision framework

Should you build an MCP server?

Choose between MCP, a direct API integration, an agent skill, static context, and browser use.

Read the guide › 05 / Engineering guide

Instrument MCP with OpenTelemetry

Set the data boundary, trace the tool operation, validate failures, and verify production coverage.

Read the guide › 06 / OpenAI distribution

List an MCP plugin in OpenAI

Prepare the endpoint, annotations, tests, policies, review materials, and post-launch measurement.

Read the guide › 07 / Claude distribution

List a plugin in Claude

Package, validate, submit, and operate a public Claude plugin with MCP support.

Read the guide ›

What is MCP observability?

MCP observability connects MCP server and tool telemetry to the complete work people and agents attempt. It covers reliability, tool usage, use cases, journeys, recurring behavior, affected users, and outcomes.

What does Flowlines show for an MCP server?

Flowlines shows observed servers, tools, clients, permitted identities, calls, common request patterns, complete journeys, outcome coverage, recurring issues, and the exact sessions behind each finding.

Is MCP latency the main Flowlines metric?

No. Latency and call status remain useful, but Flowlines focuses on what people and agents do with the server, whether the complete journey worked, and who was affected.

How is MCP analytics different from MCP monitoring?

Monitoring focuses on availability, latency, errors, and call health. MCP analytics focuses on users, adoption, use cases, journeys, outcomes, unmet needs, and product decisions. Flowlines connects both views without replacing infrastructure monitoring.

Does MCP observability require instrumentation?

Yes. The server needs compatible telemetry. The Flowlines plugin can guide a repository through an OpenTelemetry-based integration after the data boundary is reviewed.

Can Flowlines identify MCP users?

Flowlines can group calls by a person, agent, workspace, account, or MCP client when the server is permitted to report a stable identity. Analytics identity never replaces the server's authorization checks.

Does Flowlines replace Grafana, Datadog, Sentry, or OpenTelemetry?

No. Keep the operational tools you use for infrastructure, errors, logs, and traces. Flowlines adds behavioral and product analysis across users, sessions, use cases, and outcomes.

Can Flowlines notify a team about MCP behavior?

Yes. Teams can define the behavior that matters, such as a recurring failure, an unmet product request, customer risk, or commercial interest, and route the signal to Slack, email, or a webhook with the relevant evidence.

Choose your coding agent

Open the setup where you already work.

One click opens a guided instrumentation task. You approve every change.

01 Review the server

The skill checks the framework, execution boundary, and existing telemetry.

02 Set the boundary

You approve the content and identity policy before anything is exported.

03 Add telemetry

The skill makes a scoped OpenTelemetry-compatible integration.

04 Verify a journey

Run one tool flow and confirm its intent, calls, and outcome in Flowlines.

Prefer the terminal?Show one-line commands

Claude Code claude plugin marketplace add flowlines-ai/plugins && claude plugin install flowlines@flowlines

Codex codex plugin marketplace add flowlines-ai/plugins && codex plugin add flowlines@flowlines

Then use /flowlines:flowlines-mcp-observability in Claude Code or $flowlines-mcp-observability in Codex. Source and release history are in the official Flowlines plugin repository ↗.