NewIntroducing SpanlyIntroducing Spanly: observability built for MCP

Observability for MCP servers

The dedicated layer for MCP traffic, alongside the Datadog, Sentry, or New Relic you already run. Built for engineering teams shipping MCP servers in production.

Get started Live demo

Works with your existing APM via OpenTelemetry · Open-source SDK & CLI

Traces

Sessions

+17

Error Rate

17.2%

+17.2

Durations

P501ms

P953ms

P9914ms

Volume & Durations

Slowest Operations

1	initialize	—	15ms
2	Tool	echo	8ms
3	Tool	non-exis…38317556	3ms
4	Prompt	echo	3ms
5	Tool	non-exis…38313393	1ms

Top Errors

No errors in this time range 🎉

Tools

requests

Prompts

requests

Resources

requests

Server Name	Requests	Tools	Prompts	Resources	Sessions	Errors	P50	P95	P99
mcp-prod-east	14,210	12	4	9	412	18	24ms	142ms	418ms
mcp-prod-west	9,842	12	4	9	288	7	22ms	128ms	362ms
mcp-edge-eu	6,521	9	3	6	184	4	38ms	168ms	402ms
mcp-staging	2,103	9	3	6	61	28	52ms	241ms	1,284ms
mcp-dev	184	14	5	12	8	6	18ms	92ms	218ms
mcp-internal	42	4	1	2	3	0	12ms	34ms	88ms

Client Name	Connections	P50	P95	P99	Last Seen
Claude Code	82	24ms	142ms	418ms	just now
Cursor	61	32ms	188ms	521ms	1m ago
Codex CLI	34	18ms	92ms	264ms	2m ago
Windsurf	22	28ms	161ms	388ms	7m ago
Copilot	18	38ms	218ms	612ms	14m ago
Zed	7	52ms	288ms	824ms	42m ago

Tool Name	Requests	Errors	P50	P95	P99	Last Used
web_search	4,210	12	88ms	142ms	418ms	12s ago
code_exec	2,841	4	142ms	418ms	982ms	32s ago
file_read	1,921	0	4ms	12ms	38ms	1m ago
db_query	814	2	28ms	88ms	184ms	4m ago
git_diff	312	0	18ms	61ms	142ms	12m ago

Prompt Name	Requests	Errors	P50	P95	P99	Last Used
summarize	1,840	0	12ms	38ms	88ms	22s ago
extract_entities	962	0	8ms	21ms	52ms	1m ago
classify	481	1	6ms	14ms	34ms	3m ago
search	318	0	18ms	52ms	128ms	8m ago

Resource URI	Requests	Errors	P50	P95	P99	Last Used
/docs/api	2,104	0	2ms	6ms	18ms	just now
/schema/openapi.json	1,382	0	1ms	4ms	12ms	12s ago
/users/{id}	712	3	4ms	11ms	28ms	38s ago
/orders	284	0	6ms	18ms	42ms	4m ago

Request ID	Server	Session ID	Method	Start Date	Duration	Input	Output
req_8f3a912b07c2	mcp-prod-east	sess_8f3a912b	tools/call>web_search	3s ago	142ms	1.2 KB	4.8 KB
req_72c1ed40e391	mcp-prod-east	sess_8f3a912b	resources/read>/docs/api	8s ago	6ms	218 B	12.4 KB
req_a14b09c2f8d1	mcp-prod-west	sess_72c1ed40	prompts/get>summarize	12s ago	38ms	482 B	1.8 KB
req_61f8c773aa20	mcp-staging	sess_a14b09c2	tools/call>code_exec	21s ago	2,841ms	4.2 KB	128 B
req_d2e4a85117ff	mcp-edge-eu	sess_61f8c773	initialize	34s ago	15ms	128 B	482 B
req_9b1f37a8c402	mcp-prod-east	sess_8f3a912b	tools/list	52s ago	4ms	64 B	2.1 KB
req_4e07d92b1f88	mcp-dev	sess_d2e4a851	tools/call>db_query	1m ago	88ms	218 B	3.4 KB
req_31ac0e4f7728	mcp-prod-east	sess_8f3a912b	resources/list	2m ago	9ms	64 B	1.2 KB

Session ID	Client	Server	Requests	Errors	Start Date	Duration
sess_8f3a912b	Claude Code	mcp-prod-east	412	0	4m ago	12m 30s
sess_72c1ed40	Cursor	mcp-prod-east	218	2	9m ago	8m 12s
sess_a14b09c2	Codex CLI	mcp-prod-west	581	0	18m ago	22m 04s
sess_61f8c773	Windsurf	mcp-edge-eu	94	6	31m ago	4m 47s
sess_d2e4a851	Copilot	mcp-dev	312	0	1h ago	17m 21s

Error	Method	Server	Session ID	Time	Duration
Internal Error	tools/call>code_exec	mcp-staging	sess_a14b09c2	21s ago	2,841ms
Invalid Params	tools/call>db_query	mcp-dev	sess_d2e4a851	2m ago	12ms
Request Timeout	resources/read>/users/{id}	mcp-edge-eu	sess_61f8c773	12m ago	30,000ms
Rate Limited	prompts/get>classify	mcp-prod-west	sess_72c1ed40	38m ago	8ms

< 1ms

SDK overhead per request.

99.9%

Uptime SLA for data ingestion.

2 regions

US and EU, with full data residency.

OTel

Export to any OpenTelemetry APM via the CLI.

Open source

SDK and CLI source on GitHub, Apache 2.0.

Drop in the SDK. Send MCP traces to Spanly, your existing APM, or both.

WHY A DEDICATED LAYER

Your APM sees HTTP. Spanly sees MCP.

Datadog, Sentry, and New Relic do an excellent job on requests, traces, and infrastructure. They don't model the MCP protocol. Spanly does, so an on-call engineer can read a failing tool call without piecing it together from raw spans.

Signal

Datadog / Sentry / New Relic

Spanly

Protocol

HTTP POST /mcp

tools/call · resources/read · prompts/get

Protocol

HTTP POST /mcp

Spanly

tools/call · resources/read · prompts/get

Errors

500 with stack trace

Tool-call rejection with the full prompt and arguments

Errors

500 with stack trace

Spanly

Tool-call rejection with the full prompt and arguments

Performance

p95 endpoint latency

p95 per tool, per server name, per client

Performance

p95 endpoint latency

Spanly

p95 per tool, per server name, per client

Payload

Bytes in / bytes out

Tokens in / tokens out, resource read sizes

Payload

Bytes in / bytes out

Spanly

Tokens in / tokens out, resource read sizes

Clients

One client identity per session

Claude · Cursor · Windsurf · your custom client

Clients

One client identity per session

Spanly

Claude · Cursor · Windsurf · your custom client

We complement your existing stack. We don't replace it. Spanly's SDK is additive. Keep sending HTTP and infra telemetry to your APM, and send MCP-shaped traffic here.

Everything you need to monitor MCP

From real-time tracing to error tracking, Spanly captures every MCP request your server handles, from tools/call to resource reads.

initialize	30	2	1ms	2ms	15ms
tools/call	10	4	1ms	6ms	8ms
resources/read	6	2	1ms	1ms	1ms

Real-time Traces

Visualize every request and response between clients and servers with detailed timing breakdowns. Drill into a single MCP call to see the full payload, the server that handled it, and where the milliseconds went.

Error Rate

0.42%

−12%

Affected Servers

Error Code	Count	Last Occurred
Invalid Params	24	2m ago
Internal Error	11	14m ago
Request Timeout	7	1h ago
Method Not Found	5	3h ago
Connection Closed	3	8h ago

Error Tracking

Catch errors before your users do. Track error codes, frequencies, and stack traces across every server and client – grouped so a recurring failure shows up once, not a thousand times.

Slowest operations

p50p95p99

tools/call: web_search

58380890

tools/call: code_exec

210480720

resources/read: /docs/api

76280540

prompts/get: search

22210320

tools/call: file_read

82140180

initialize

184265

Performance Metrics

Monitor request durations, identify bottlenecks, and track performance trends over time. p50, p95, p99 broken down by server and tool, so you can tell a single slow tool apart from a regressing deployment.

Cursor

14.1k+9%

Error rate0.18%

Codex CLI

9.7k+14%

Error rate0.21%

Claude Code

18.2k+28%

Error rate0.09%

Windsurf

6.3k+41%

Error rate0.27%

Copilot

11.5k−3%

Error rate0.14%

Cline

4.8k+22%

Error rate0.33%

Zed

3.2k+52%

Error rate0.41%

Continue

2.1k+7%

Error rate0.19%

Analytics

Aggregate usage across servers and clients to spot trends and tune performance. See which prompts, tools, and resources are actually getting used – and which ones aren't earning their keep.

DATA RESIDENCY

Your data, in your region

Pick US or EU when you create a project. Telemetry stays in the region you chose. GDPR-friendly by design, with full data residency.

2 regions

US and EU ingest endpoints. Pick one per project; data never leaves it.

1 jurisdiction

EU customers keep all telemetry inside the EU. GDPR-ready, no US-side replication.

0 cross-region copies

Daily backups live in the same region as your live data. Never replicated elsewhere.

Operate at scale

Built for the people on call

Live status for the team room, alerts before customers complain, session traces for fast root-cause, and an audit log of everything that happened.

Status board

Built for the office TV

Pin always-on status boards to any screen. Full-screen, auto-refresh, no chrome.

Auto-refresh · 30sLive

Uptime

99.97%

p95

142ms

Errors

Open incidents

Alerts

Alerts, before users notice

Set thresholds on error rate, p95/p99, or traffic, scoped to any server, client, or tool. Routed to email, Slack, and signed webhooks.

Triggered just now

p99 latency exceeded threshold on mcp-prod-east

p99 > 500ms for 5mjust now

Error rate spiked on tool code_exec

errors > 2% for 10m6m ago

Traffic dropped 40% on client Cursor

volume drop > 30% for 15m24m ago

Sessions

Trace every session, end to end

Group requests by session to see the full arc of an interaction: every tool call, every error, every retry.

Real-time

sess_72c1ed40· started 12m ago12m 04s
40 req2 err
sess_8a39f10c· started 3m ago3m 22s
18 req0 err
sess_5d20b4ee· ended 2h ago41m 18s
112 req5 err
sess_19b7cc28· ended 5h ago1m 02s
7 req0 err

Audit log

A receipt for every action

Tamper-evident trail of every MCP call and config change.

12:42:08AUTHuser@acme.com
signed in via SSO
12:41:55WRITEuser@acme.com
changed alert threshold on mcp-prod-east
12:39:21ADMINuser@acme.com
revoked API key k_8f3a…
12:38:02READagent:claude-code
accessed session sess_72c1ed40

Live in 5 minutes

Drop the SDK into your MCP server. No schema to maintain, no agent process, no rebuild.

For your server

Instrument your MCP server

Drop the SDK into your TypeScript or Python server, wrap any binary with the CLI, or ship Spanly as a Docker sidecar. Every prompt, tool call, and resource gets traced – no schema, no agent process, no rebuild.

Install

$ npm install @spanly/sdk

Usespanly-setup.ts

import { SpanlyClient } from "@spanly/sdk"

const spanly = new SpanlyClient({
  apiKey: process.env.SPANLY_API_KEY,
})

spanly.monitor(mcpServer)

Also

Query Spanly from your editor

Spanly also ships an MCP server of its own. Point Claude Code, Cursor, or any MCP client at it to search traces and triage errors without leaving your IDE.

$ claude mcp add --transport http spanly https://mcp.spanly.com/mcp

Start monitoring your MCP servers

Engineering teams: add the MCP layer to your observability stack in under 5 minutes.

Get started Live demo