Flowlines

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

MCP observability is monitoring how a Model Context Protocol server behaves in production and how people use it: which users and AI clients call it, which tools they use, what they are trying to do, where sessions fail and how fast each tool responds.

Infrastructure monitoring answers whether the server is up and fast. MCP observability adds the usage layer: users, sessions, use cases, outcomes and the signals your product, engineering and sales teams act on. Flowlines provides that usage layer for MCP servers and works alongside Grafana, Datadog and OpenTelemetry rather than replacing them.

Updated October 22, 2026. Sources: the MCP specification, the OpenTelemetry MCP semantic conventions and request metadata (SEP-414).

Signal	What it tells you	How to measure it	A starting alert
Availability	Can clients connect and list tools?	Health and readiness probes; failed initialize and tools/list requests	Probe failing for 2 minutes
Traffic	How much each tool is used	Calls per second by server, environment and tool	Calls drop 50% against the same hour last week
Errors	Which tools fail, including errors returned inside a successful response	Error rate by tool, counting tool results that report an error	Error rate above 5% for 5 minutes with at least 100 calls
Latency	Which tools are slow for users	p50, p95 and p99 duration by tool	p95 above 2 seconds for 10 minutes
Users and AI clients	Who uses the server, from Claude, ChatGPT, Cursor or others, and who comes back	Users, returning users and sessions by AI client in Flowlines	An important account stops using the server
Use cases	What people are trying to do, not just which tool ran	Top use cases and their tool paths in Flowlines	A new use case grows quickly
Outcomes	Whether the job got done, beyond a successful call	Sessions that finished, stalled or repeated in Flowlines	A recurring job keeps ending unfinished
Product and buying signals	Requests the MCP cannot serve yet, and evaluation questions	Product needs and buying intent in Flowlines	Notify Slack when someone asks about seats or security

Free starter kit

Copy the alerts and dashboard

Example Prometheus alert rules with tests, a Grafana dashboard for calls, errors and p50/p95/p99 latency by tool, and a production checklist. They use example metric names; adapt them to your own telemetry.

• Grafana dashboard (JSON)
• Prometheus alert rules
• Alert rule tests
• MCP production checklist

Looking specifically for usage and product analytics? Explore MCP server, tool and session analytics.

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 to investigate

Affected sessions, repeated calls, failures, corrections, and reported outcomes that conflict with observed results.

04 What to do next

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

Synthetic data · interactive product example

Journey reconstruction

A successful tool call is not a successful journey.

Follow the captured calls, repeated attempts and reported result. See the client and permitted identity when supplied. Missing outcome context stays unknown, not automatically successful or abandoned.

**Session 7c1e · Maya R.**Northstar · billing-mcp Claude2.4 s

Northstar was charged twice for order 1932 in March. Find it and refund the duplicate.

• ✓ get_customer Northstar · cus_8KQ2118 ms
• ✓ search_orders 3 orders in March342 ms
• ✓ get_order ord_1932 · €1,240205 ms
• !list_payments Slow · paged twice601 ms
• ✓ get_invoice inv_0457 charged twice231 ms
• ✓ create_refund €1,240 refunded702 ms

Thanks. Could we roll this out to our 80-person finance team, with SSO?

Buying intent detected · 80 seats · SSO

Top use cases With tool paths

Find a customer's unpaid invoices search_customers → list_invoices 27%↑ 4%

Issue a refund for a duplicate charge get_charge → create_refund 19%↑ 11%

Explain why a payment failed get_payment → get_events 15%↑ 2%

Upgrade or downgrade a subscription get_subscription → update_plan 12%↑ 6%

Export last month's revenue by plan list_invoices → export_csv 9%↑ 1%

Synthetic data · interactive product example

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
Usage analytics (Flowlines)	Who uses the server, what are they trying to do, what keeps failing, and who is affected?	Engineering, product, customer, sales
Outcomes (Flowlines)	What result was reported, what do the calls support, and what remains unknown?	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 friction before a ticket.

Spot an important account repeatedly trying to finish the same job. Use failed resolutions and observed frustration to choose a useful intervention.

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.

Sessions with buying intent 18 +50% vs previous period

RuleNotify #sales-intent when a user asks about pricing, seats or a security review

Flowlines APP #sales-intent · after analysis

A user at Northstar is evaluating 80 seats

Maya R. asked to roll out to an 80-person finance team with SSO, right after a refund went through in Claude.

“Could we roll this out to our 80-person finance team, with SSO?”

Claude · session 7c1e Open session ›

Real-time after analysis, or a daily or weekly digest · Slack · Email · Webhook

Synthetic data · interactive product example

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

Delivery follows analysis; product-need grouping can add delay. Explore business KPIs and notification rules ›

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 / Stack guide

Add MCP analytics to your existing stack

Keep OpenTelemetry, Grafana or Datadog for server health and add users, clients, use cases and signals.

Read the guide › 07 / Debugging guide

MCP error codes and failed tool calls

Tell protocol errors from tool errors, read each JSON-RPC code, and find the users who hit them.

Read the guide › 08 / Metrics guide

MCP server KPIs

Measure activation, weekly retention and calls per completed job instead of call volume.

Read the guide › 09 / Tool design

Why agents ignore your MCP tools

Find tools that are never called, picked by mistake or called over and over, and fix them.

Read the guide › 10 / Spec update

MCP analytics after the stateless spec

Group sessions, identify clients and time retried calls without the initialize handshake.

Read the guide › 11 / OpenAI distribution

List an MCP plugin in OpenAI

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

Read the guide › 12 / Customer story

What Melaya learned from its first MCP tool calls

How Melaya uses Flowlines to see which tools people use, from which assistant, and what they try to do.

Read the guide › 13 / 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 is monitoring how an MCP server behaves in production and how people use it: which users and AI clients call it, which tools they use, what they are trying to do, where sessions fail and how fast tools respond. Flowlines provides the usage side and works alongside the monitoring you already run.

What does Flowlines show for an MCP server?

Flowlines shows observed servers, tools, clients, permitted identities, calls, request patterns, related sessions, outcome coverage and recurring issues. Coverage depends on the integration. An observed session is not necessarily the assistant's complete conversation.

Is MCP latency the main Flowlines metric?

No. Latency and call status remain useful, but Flowlines focuses on what people and agents attempt, where the observed workflow gets stuck and who is affected. Reported outcomes are reviewed alongside the available calls.

Does a missing outcome mean a user abandoned the workflow?

No. Missing outcome context means the result is unknown. A workflow may finish outside the server, or its client may not report a result. Flowlines does not treat silence alone as proof of abandonment.

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. Configure notifications for recurring failures, unmet product requests, buying intent or custom behavior signals. Route findings to Slack, email or a webhook with real-time delivery after analysis, or daily and weekly digests. Analysis and grouping affect delivery time.

Your own server. Your own data.

Start where you already work.

one connection, then your use case

Start free

01 Connect Flowlines

Add the MCP connection or the official plugin.

02 Ask to onboard

Get a plan for the MCP server in your repository.

03 Approve the plan

Your assistant adds OpenTelemetry instrumentation and runs the tests.

04 Check onboarding

Ask Flowlines to verify the telemetry and fix any gaps.

Need manual setup? View the setup commands ›