Connect Claude, Cursor and other AI agents to your Maple telemetry over the Model Context Protocol: endpoints, authentication, and every tool the server exposes.
Maple runs a Model Context Protocol (MCP) server. Each connection works inside one organization. From there an agent can query services, traces, logs and infrastructure, triage error issues, edit dashboards, manage alert rules, SLOs, uptime monitors and ingest rules, update status pages, read security audit runs, and query the databases and APIs the organization connected as data sources.
| |
|---|
| Endpoint (US) | https://api.maple.dev/mcp |
| Endpoint (EU) | https://api.eu.maple.dev/mcp |
| Transport | Streamable HTTP |
Manifest (server.json) | maple.dev/.well-known/mcp.json · api.maple.dev/.well-known/mcp.json |
| Registry name | dev.maple/maple |
| Auth | Maple API key as Bearer token, or OAuth 2.1 |
| Rate limit | 120 requests per 10 seconds per key or user; over it, 429 with Retry-After: 10 |
Use the endpoint of your organization’s region. The examples below use the US endpoint; for an EU organization replace api.maple.dev with api.eu.maple.dev.
Connecting a client
Any MCP client that speaks Streamable HTTP can connect. Settings → MCP in the dashboard shows the endpoint for your region and ready-made configuration for common clients. There are two ways to authenticate. Both are described in more detail on Authentication.
API key. Create a key under Settings → MCP or Settings → Keys and pass it as a Bearer token:
{
"mcpServers": {
"maple": {
"type": "http",
"url": "https://api.maple.dev/mcp",
"headers": { "Authorization": "Bearer maple_ak_…" }
}
}
}
For Claude Code: claude mcp add --transport http maple https://api.maple.dev/mcp --header "Authorization: Bearer maple_ak_…".
OAuth. Clients that support the MCP authorization flow need no key. The server publishes its protected-resource metadata at https://api.maple.dev/.well-known/oauth-protected-resource/mcp and its authorization server metadata at https://api.maple.dev/.well-known/oauth-authorization-server. Dynamic client registration and PKCE (S256) are supported, so the client needs only the endpoint URL. It opens a browser sign-in on first use.
Requests are scoped to the organization the key belongs to, or the one chosen at sign-in. A user in several organizations picks one during the OAuth consent step.
The server exposes the tools below. Read-only tools are marked read; the rest change data in your organization. tools/list returns the current set with full parameter schemas.
A manage_… tool holds one resource’s writes: it takes an action (such as create, update or delete) and that action’s parameters. The names these replaced, such as create_slo, still run.
Tools that take an alert rule, alert destination, dashboard or error issue ID accept either its UUID or its REST API ID (alrt_…, dest_…, dash_…, iss_…). list_alert_destinations, list_dashboards, get_dashboard and create_dashboard return both. The REST API also accepts the UUID in place of its prefixed ID.
Services and discovery
| Tool | Access | What it does |
|---|
list_services | read | Active services with throughput, error rate and P95 latency |
diagnose_service | read | One service’s health, top errors, recent traces and logs, and the platform resources behind it |
get_service_top_operations | read | A service’s top operations (endpoints or spans), ranked by a chosen metric |
profile_hotspots | read | Where a service spent CPU or allocated memory: its heaviest functions from continuous profiling |
service_map | read | Service-to-service dependencies with call counts, error rates and latency per edge |
compare_periods | read | Error rate, throughput and P95 across two periods, overall and per service, with regressions flagged |
explore_attributes | read | Attribute keys and their values for filtering; source=services lists environments and commit SHAs |
list_metrics | read | Custom metrics with type, unit, monotonicity and data volume |
describe_warehouse_tables | read | Tables and columns available to raw SQL, with sorting keys and notes on units and casing |
service_deployments | read | Versions (commit SHAs) each service ran, with traffic, error rate and P95 per version |
route_usage | read | HTTP endpoints per service with request count, error rate, P95 and first and last seen, up to 90 days |
db_query_volume | read | Database query shapes ranked by call volume per service and database, with errors and latency |
Traces, logs and queries
| Tool | Access | What it does |
|---|
search_traces | read | Find traces by service, duration, error status, HTTP method, span name or one span attribute |
find_slow_traces | read | The slowest traces with p50, p95, min and max for context |
inspect_trace | read | Span tree and logs for one trace |
inspect_span | read | Full attribute set for one span; decodes messages and tool calls on AI agent spans |
search_logs | read | Log entries, newest first, filtered by service, severity, body text, trace or span |
mine_log_patterns | read | Cluster log messages into templates with counts and a severity and service breakdown |
compare_log_patterns | read | Log templates that are new, gone, or whose share doubled or halved between two windows, such as before and after a deploy |
compare_operations | read | A service’s operations that are new, gone, or whose share, error rate or p95 changed between two windows, such as before and after a deploy |
query_data | read | Aggregate traces, logs, metrics or product events into a time series or top-N breakdown |
run_sql | read | Run one read-only ClickHouse SELECT. The model sees the first 100 rows and the full row count; see the SQL reference |
Errors
| Tool | Access | What it does |
|---|
find_errors | read | Errors grouped by type with counts, affected services and a stable fingerprint |
error_detail | read | Sample traces and correlated logs for one error fingerprint |
list_error_issues | read | Error issues with workflow state, counts, assignee and lease holder |
list_error_issue_events | read | An issue’s audit log: state changes, claims, comments, agent notes and fix proposals |
get_investigation | read | One investigation by inv_… id: its subject, status and the AI diagnosis with evidence |
list_error_incidents | read | Time-bounded flare-ups under an error issue (first seen and regressions) |
claim_error_issue | write | Take a lease on an issue so other agents do not duplicate the work |
release_error_issue | write | Give up your lease, optionally moving the issue to another state |
transition_error_issue | write | Move an issue to another workflow state |
transition_error_issues | write | Move up to 200 issues to one workflow state, with a note on each |
merge_error_issues | write | Fold up to 50 duplicate issues into one; each merged issue is archived pointing at the kept one |
set_issue_severity | write | Set or clear an issue’s triage severity |
comment_on_error_issue | write | Add a comment or agent note to an issue’s timeline |
propose_fix | write | Record a proposed fix and move the issue to in_review |
link_pull_request | write | Attach a GitHub pull request to an issue; Maple verifies the fix after it merges |
register_agent | write | Register an LLM agent so it can claim and transition issues. Needs a signed-in user, not an API key |
get_error_notification_policy | read | The error notification policy: destinations, toggles, and when the first notification goes out |
update_error_notification_policy | write | Choose whether error incidents notify alert destinations, and which ones. Org admins only |
Alerting
| Tool | Access | What it does |
|---|
list_alert_rules | read | Alert rules with severity, signal type and condition |
get_alert_rule | read | One rule’s full configuration: thresholds, filters, evaluation settings and destinations |
list_alert_destinations | read | Notification destinations with id, type and delivery health |
manage_alert_destination | write | Run a destination’s test, rename, turn off or delete it, or add an email destination |
list_alert_incidents | read | Triggered alert incidents, open and resolved, with the last observed value |
acknowledge_alert_incident | write | Acknowledge an open incident, which pauses its reminders, or clear the acknowledgement |
get_incident_timeline | read | Trigger, notification and resolution times for one rule’s incidents, or all rules’ |
list_alert_checks | read | A rule’s recent evaluations with observed value, threshold and sample count |
preview_alert_rule | read | Replay a saved or draft rule over past data: each window’s verdict and skip reason |
create_alert_rule | write | Create an alert rule from a template or from signal type, comparator and threshold |
update_alert_rule | write | Change the fields you pass on an alert rule |
delete_alert_rule | write | Delete an alert rule and its incident history. Requires confirm=true |
list_escalation_chains | read | Escalation chains with their steps, repeats and the rules using them |
manage_escalation_chain | write | Create, change or delete an escalation chain: destinations paged step by step, waiting for an acknowledgement between steps |
list_maintenance_windows | read | One-off and weekly maintenance windows with their schedule, matchers and next occurrence |
manage_maintenance_window | write | Create, change or delete a maintenance window that silences matching rules once or every week; can keep those hours out of anomaly baselines |
list_oncall_schedules | read | On-call schedules with their layers and who is on call now |
who_is_on_call | read | Who is on call for a schedule at an instant, why, and who is next |
manage_oncall_schedule | write | Create, change or delete a schedule that rotates workspace members in layers, or add and remove an override that puts one member on call |
list_alert_silences | read | Active and scheduled alert silences, or ended ones, with their matchers and window |
manage_alert_silence | write | Hold back notifications for matching rules for a duration or until a time, or end a silence so they resume |
SLOs and uptime monitors
| Tool | Access | What it does |
|---|
list_slos | read | Every SLO with its current SLI, error budget left and worst burn rate, breaching ones first |
inspect_slo | read | One SLO in full: config, error budget, the burn rate of each window and its burn-rate alerting |
manage_slo | write | Create, change or delete an availability or latency SLO on one service, with burn-rate alerts |
list_uptime_monitors | read | HTTP, TCP and DNS checks and heartbeats with their status, last check and recent pass rate, down first |
manage_uptime_monitor | write | Create, pause, change or delete an HTTP, TCP or DNS check or a heartbeat; creating a heartbeat returns its ping URL |
The write tools here need the org admin or engineer role.
Status pages
| Tool | Access | What it does |
|---|
get_status_page | read | Every status page, or one page as visitors see it, with component status and open incidents |
manage_status_page | write | Create a page as a draft, replace its settings and components, set its custom domain, publish it, or post an incident or maintenance update |
Dashboards
| Tool | Access | What it does |
|---|
list_dashboards | read | Dashboards with widget counts and timestamps |
get_dashboard | read | One dashboard’s full configuration, every widget included |
describe_dashboard_schema | read | What a widget can be: panel types, data sources, units, aggregations and display options |
inspect_chart_data | read | Run a widget’s query and report row counts, series statistics and a health verdict |
create_dashboard | write | Create a dashboard from a template, simplified widget specs or full JSON |
update_dashboard | write | Change a dashboard’s name, description or time range |
delete_dashboard | write | Delete a dashboard with its widgets and versions |
add_dashboard_widget | write | Add one widget, from the query builder, raw SQL or a funnel |
update_dashboard_widget | write | Replace one widget with a full widget object |
remove_dashboard_widget | write | Remove one widget |
reorder_dashboard_widgets | write | Move or resize widgets |
replace_dashboard_widgets | write | Replace every widget in one validated write |
Session replays and product events
| Tool | Access | What it does |
|---|
search_sessions | read | Find browser session replays by user, client, errors, duration or what happened in them |
get_session_transcript | read | A session replay as a text transcript of navigation, clicks, console, network and errors |
get_session_traces | read | The backend traces a browser session produced |
list_product_events | read | Product event names with how often each fired and how many sessions and people it reached |
query_cohort | read | Who did one thing and did not do another: how many, out of how many, and who |
query_funnel | read | Conversion funnel over product events, per person or per account, with conversion and drop-off |
query_paths | read | What people do in the steps after, or before, one event or page |
query_retention | read | Retention cohorts: who first did one thing, and how many came back each day, week or month |
list_users | read | The end users your apps identified, with sessions, requests, errors and their busiest route |
inspect_user | read | One end user: sessions, their latest events, MCP sessions, issues and failed requests |
Agent sessions
| Tool | Access | What it does |
|---|
list_agent_sessions | read | AI agent sessions with agent, models, LLM and tool calls, failures, tokens and cost |
get_agent_session | read | One agent session: verdict, checks, findings, timing, turns, tokens and cost |
get_agent_session_transcript | read | One agent session step by step: prompts, replies, tool calls and results, sub-agents |
get_agent_tools_overview | read | Calls, failures and latency per agent tool, compared with the previous window |
get_agent_tool_error | read | One agent tool failure group with affected sessions and sample calls |
Setup
| Tool | Access | What it does |
|---|
audit_setup | read | Check the whole organization setup: alert routing, error notifications and per-service ingest coverage |
get_instrumentation_recommendations | read | Span and resource attribute problems found in your live data |
list_integrations | read | Connected integrations, what each one feeds, and which resources are failing or stale |
list_ingest_sources | read | Everything that sends data to the organization, worst health first, and when each last sent data |
manage_ingest_source | write | Pause, resume, rename, limit or delete an ingest source |
ingest_freshness | read | Newest received timestamp per signal, with its lag |
ingest_usage | read | Spans, log records and metric data points ingested per service, with org totals |
Ingest rules
| Tool | Access | What it does |
|---|
list_ingest_rules | read | The rules that drop or redact telemetry before Maple stores or bills it, in the order they run |
preview_ingest_rule | read | Run a saved or draft rule over recent traces or logs and count what it would drop or redact |
manage_ingest_rule | write | Add, change or delete a drop or redact rule; it applies to new data within 30 seconds |
The write tools here need the org admin or engineer role.
Data sources
| Tool | Access | What it does |
|---|
list_data_sources | read | The connected databases and APIs; query finds a topic, data_source lists a source’s tables, and entries adds their fields |
query_data_source | read | Run one read-only SQL or resource query against a data source; explain=true returns only the plan |
Infrastructure
| Tool | Access | What it does |
|---|
list_infra | read | Hosts, Kubernetes, Docker containers and integration resources, closest to a limit first |
inspect_infra | read | One host, pod, node, workload, container or integration resource in depth |
Security
| Tool | Access | What it does |
|---|
list_security_findings | read | Code audit findings, vulnerable dependencies, scanner probes that got a 2xx and outdated runtimes, worst first, or one area in full |
inspect_security_finding | read | One finding in full, or whether an advisory (CVE, GHSA) affects any repository or service |
list_security_audit_runs | read | Code security audit runs, newest first, with status, cost and findings, and this month’s audit spend against its limit |
inspect_security_audit_run | read | One audit run in full: what it covered, every claim it reported, and its step log. Org admins and engineers only |
Integrations
| Tool | Access | What it does |
|---|
sync_railway | write | Poll Railway now and report each environment’s last sync |
sync_vercel | write | Sync Vercel now: projects, deployments and the state of Maple’s drains |
manage_scrape_target | write | Start, pause, change or stop scraping a Prometheus endpoint that needs no credentials |
These are admin-only. Connecting a provider, and adding a scrape credential, stay in the dashboard, under Sources or Settings → Integrations.
Search Console
| Tool | Access | What it does |
|---|
search_console_queries | read | Google search queries from the connected Search Console: clicks, impressions, CTR and position, against the previous period |
search_console_pages | read | Search landing pages joined with Maple web analytics: sessions, bounce rate and, optionally, conversions |
Feedback
| Tool | Access | What it does |
|---|
send_maple_feedback | write | Tell the Maple team about a bug, a missing capability or a misleading doc: its kind, the agent, and why |
list_maple_feedback | read | Maple team admins only: read the feedback agents sent. Refused for any other organization |
The same feedback can be sent over the REST API with POST /v2/agent_feedback.
Prompts and resources
The server also provides three prompts (incident_triage, latency_analysis, debug_errors) and two resources: maple://instructions, which explains Maple’s data model to the model, and maple://data-sources, which lists the organization’s connected data sources.