Skip to content
actionlake
Start free

Connectors · Observability & analytics

Raygun MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Raygun and the rest of your systems. It gives your agent 53 Raygun actions (36 reads, 11 writes and 6 that wait for a confirmation) and holds the Raygun credential itself, so the agent never does. It paces Raygun's limits and records every call.

Connect Raygun freeSee pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "raygun.applications.list",  intent: "check which Raygun account is connected"}# List applications · read · 1 upstream call
  • 53actionsin one signed file
  • 36readlook, never change
  • 11writecreate and update
  • 6wait for a yesdestructive, confirmed first

Set up

Connect Raygun in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect Raygun.

    Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • access_tokenRaygun Personal Access Token (Raygun app > your avatar > My settings > Personal Access Tokens)
    account { op: "connections.requirements", service: "raygun" }
# free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "raygun.applications.list" }# list applications · read · 1 upstream callcheck { action: "raygun.deployments.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Raygun at a glance

Sign-in
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
access_token
Limits we pace to
300 calls a minute, per connection
API covered
Raygun API v3 (OpenAPI 3.0.3, info.version 3.0)api.raygun.com/v3
Built from
Raygun's documentation, read 23 October 2026api.raygun.ioraygun.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
29 of 36 reads, for up to 5 minutes; a write clears what it affects
Shared entities
3, so ask can line Raygun up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Raygun.

53 actions in 16 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 36readlook, never change
  • 11writecreate and update
  • 6destructivewait for a confirmation

  1. Error groups

    9

    4 read · 5 write · 0 destructive

    List error groups for an application · Get error group by identifier · Resolve error group · Activate error group

  2. Deployments

    8

    3 read · 4 write · 1 destructive

    List deployments for an application · Create deployment · Get deployment by identifier · Delete deployment

  3. Source maps

    5

    2 read · 1 write · 2 destructive

    List source maps for an application · Get source map by identifier · Deletes a sourcemap by identifier · Deletes all source maps for an application

  4. Applications

    4

    3 read · 0 write · 1 destructive

    List applications · Get application by identifier · Get application by api key · Regenerate application api key

  5. Invitations

    4

    2 read · 1 write · 1 destructive

    Send an invitation · List invitations · Get invitation by identifier · Revoke invitation

  6. Error instances

    3

    3 read · 0 write · 0 destructive

    List error instances for an error group · Get error instance by identifier · Get latest error instance for an error group

  7. Flutter symbols

    3

    2 read · 0 write · 1 destructive

    List Flutter symbols for an application · Get Flutter symbol by identifier · Delete Flutter symbol by identifier

  8. Metrics

    3

    3 read · 0 write · 0 destructive

    Time-series error metrics · Time-series page metrics · Histogram page metrics

8 more areas · 14 actions
  • Apm issues 2
  • Apm traces 2
  • Customers 2
  • Pages 2
  • Sessions 2
  • Teams 2
  • Apm hotspots 1
  • Plans 1

Top actions

The Raygun API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 9 of Raygun's 9 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
raygun.error_groups.listList error groups for an applicationList error groups for an application.readmonitoring.alert.list51 connectors
raygun.deployments.listList deployments for an applicationList deployments for an application.readdevops.deployment.list22 connectors
raygun.error_groups.getGet error group by identifierGet error group by identifier.readmonitoring.alert.get33 connectors
raygun.deployments.createCreate deploymentCreate deployment.writedevops.deployment.create17 connectors
raygun.error_groups.resolveResolve error groupResolve error group.writemonitoring.alert.close8 connectors
raygun.metrics.pages_time_seriesTime-series page metricsTime-series page metrics.readmonitoring.metric.query9 connectors
raygun.metrics.errors_time_seriesTime-series error metricsTime-series error metrics.readmonitoring.metric.query9 connectors
raygun.deployments.deleteDelete deploymentDelete deployment.destructivedevops.deployment.delete9 connectors
raygun.error_groups.activateActivate error groupActivate error group.writemonitoring.alert.reopen2 connectors
raygun.customers.listList customers for an applicationList customers for an application.readthis connector
raygun.pages.listList pages for an applicationList pages for an application.readthis connector
raygun.plans.listList plansList plans.readthis connector

Try it

Prompts to paste into Claude.

Each one names the Raygun actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Which Raygun alerts are open right now? Group them by service.

    callsraygun.error_groups.list

  2. Writewrite

    Create deployment in Raygun. Show me exactly what you will send before you save it.

    callsraygun.deployments.create

Governance for Raygun

Destructive actions wait for a yes.

6 Raygun actions are destructive. These are all of them:

  • Delete deploymentraygun.deployments.delete
  • Deletes a sourcemap by identifierraygun.source_maps.delete
  • Delete Flutter symbol by identifierraygun.flutter_symbols.delete
  • Deletes all source maps for an applicationraygun.source_maps.delete_all
  • Regenerate application api keyraygun.applications.regenerate_api_key
  • Revoke invitationraygun.invitations.revoke

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

doraygun.deployments.deleteconfirm_policy: human

Delete deployment?

intent: the user asked me to delete deployment

run suspended · waiting for a named person · key raygun-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "raygun-agent",  allowed_actions: ["raygun.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "raygun.deployments.delete", approver: "[email protected]" },    { match: "raygun.source_maps.delete", approver: "[email protected]" },    { match: "raygun.flutter_symbols.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to Raygun only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Raygun costs on actionlake.

Every Raygun action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Raygun refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 53 Raygun actions
  • 13actions pageeach page of a long list is one call
  • 29reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Raygun action.

53 actions by area: the id your agent calls, what it does, and its effect.

Error groups9
  • raygun.error_groups.activateActivate error groupwrite
  • raygun.error_groups.commentCreate error group commentwrite
  • raygun.error_groups.getGet error group by identifierread
  • raygun.error_groups.ignoreIgnore error groupwrite
  • raygun.error_groups.listList error groups for an applicationread
  • raygun.error_groups.list_for_deploymentList error groups from a deploymentread
  • raygun.error_groups.list_for_latest_deploymentList error groups from the latest deploymentread
  • raygun.error_groups.permanently_ignorePermanently ignore error groupwrite
  • raygun.error_groups.resolveResolve error groupwrite
Deployments8
  • raygun.deployments.createCreate deploymentwrite
  • raygun.deployments.create_by_api_keyCreate deployment with api keywrite
  • raygun.deployments.deleteDelete deploymentdestructive
  • raygun.deployments.getGet deployment by identifierread
  • raygun.deployments.get_latestGet the latest deploymentread
  • raygun.deployments.listList deployments for an applicationread
  • raygun.deployments.reprocess_commitsReprocess deployment commitswrite
  • raygun.deployments.updateUpdate deployment detailswrite
Source maps5
  • raygun.source_maps.deleteDeletes a sourcemap by identifierdestructive
  • raygun.source_maps.delete_allDeletes all source maps for an applicationdestructive
  • raygun.source_maps.getGet source map by identifierread
  • raygun.source_maps.listList source maps for an applicationread
  • raygun.source_maps.update_uriUpdate the URI for a sourcemapwrite
Applications4
  • raygun.applications.getGet application by identifierread
  • raygun.applications.get_by_api_keyGet application by api keyread
  • raygun.applications.listList applicationsread
  • raygun.applications.regenerate_api_keyRegenerate application api keydestructive
Invitations4
  • raygun.invitations.createSend an invitationwrite
  • raygun.invitations.getGet invitation by identifierread
  • raygun.invitations.listList invitationsread
  • raygun.invitations.revokeRevoke invitationdestructive
Error instances3
  • raygun.error_instances.getGet error instance by identifierread
  • raygun.error_instances.get_latestGet latest error instance for an error groupread
  • raygun.error_instances.listList error instances for an error groupread
Flutter symbols3
  • raygun.flutter_symbols.deleteDelete Flutter symbol by identifierdestructive
  • raygun.flutter_symbols.getGet Flutter symbol by identifierread
  • raygun.flutter_symbols.listList Flutter symbols for an applicationread
Metrics3
  • raygun.metrics.errors_time_seriesTime-series error metricsread
  • raygun.metrics.pages_histogramHistogram page metricsread
  • raygun.metrics.pages_time_seriesTime-series page metricsread
Apm issues2
  • raygun.apm_issues.getInvestigate an APM issueread
  • raygun.apm_issues.searchSearch APM issuesread
Apm traces2
  • raygun.apm_traces.getInvestigate an APM traceread
  • raygun.apm_traces.searchSearch APM tracesread
Customers2
  • raygun.customers.getGet customer by identifierread
  • raygun.customers.listList customers for an applicationread
Pages2
  • raygun.pages.getGet page by identifierread
  • raygun.pages.listList pages for an applicationread
Sessions2
  • raygun.sessions.getGet session by identifierread
  • raygun.sessions.listList sessions for an applicationread
Teams2
  • raygun.teams.getGet team by identifierread
  • raygun.teams.listList teamsread
Apm hotspots1
  • raygun.apm_hotspots.searchSearch APM hotspotsread
Plans1
  • raygun.plans.listList plansread

Questions

The Raygun MCP server, answered.

Is there a Raygun MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 53 Raygun actions across error groups, deployments, source maps and applications, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Raygun.

What do I need to connect Raygun?

Raygun Personal Access Token (Raygun app > your avatar > My settings > Personal Access Tokens). The free call account { op: "connections.requirements", service: "raygun" } lists exactly what to paste.

Can an AI agent delete or change things in Raygun?

Only if its key allows it, and only with an explicit confirmation. 6 Raygun actions are destructive, including delete deployment, deletes a sourcemap by identifier and delete Flutter symbol by identifier. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Raygun API limit?

actionlake paces every call to the limits in the Raygun service file: 300 calls a minute per connection. Repeated reads are answered from cache (29 Raygun actions can be), which never reaches Raygun.

What does a Raygun action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (13 Raygun actions page). Cache hits, searches, dry runs and calls Raygun refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Raygun API does it cover?

The Raygun API v3 (OpenAPI 3.0.3, info.version 3.0) at api.raygun.com/v3. It is built from Raygun's documentation as read on 23 October 2026. 53 actions in 16 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Raygun data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Raygun credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

More connectors like Raygun

Shares the most action names with

Joins with, on shared entities

Browse

actionlake is independent. It is not made or endorsed by Raygun; the name is the vendor's own. Counts are from the Raygun service file, version 1.0.0.

Give your agent Raygun today.

Connect Raygun freeSee pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.