Mezmo for AI agents

Mezmo is a log management platform that collects, processes, and analyzes telemetry data for engineering and operations teams monitoring production systems. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

DevOps and monitoringAPI keyMCP + RESTmezmo.com
AUDIT LOG · MEZMOPOLICY: acme-support
09:41:07 · claude · u_8f2read
mezmo.list_keys
List API Keys✓ allowed · 212ms
09:41:08 · claude · u_8f2read
mezmo.get_key
Get API Key✓ allowed · 164ms
09:41:09 · claude · u_8f2write
mezmo.create_key
Create API Key✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
mezmo.delete_key
Delete API Key✕ blocked · policy: deny
EVERY MEZMO CALL, ON THE RECORD
01 · USE CASES

What agents do in Mezmo.

01

Check ingestion status

Look up whether logs are flowing correctly into a pipeline, a read-only health check.

02

Search recent alert configurations

List preset alerts configured for a view to confirm on-call coverage is set up correctly before a release.

03

Approve before deleting a view

Require approval before deleting a saved view, since dashboards and alerts may reference it.

02 · ACTIONS

36 Mezmo actions, graded by risk.

Every Mezmo action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

14

Look things up. Allowed by default.

  • mezmo.get_key
    Get API Key
  • mezmo.get_view
    Get View Details
  • mezmo.get_alert
    Get Preset Alert
  • mezmo.list_keys
    List API Keys
  • mezmo.get_member
    Get Member
  • mezmo.list_views
    List Views
  • mezmo.list_alerts
    List Preset Alerts
  • mezmo.get_category
    Get Category
  • mezmo.list_members
    List Members
  • mezmo.list_pipelines
    List Telemetry Pipelines
  • mezmo.get_stream_config
    Get Stream Configuration
  • mezmo.get_index_rate_alert
    Get Index Rate Alert Configuration
  • mezmo.get_ingestion_status
    Get Ingestion Status
  • mezmo.get_ingestion_exclusion
    Get Ingestion Exclusion Rule

write

15

Create and change things. Allow, or ask the user first.

  • mezmo.create_key
    Create API Key
  • mezmo.update_key
    Update API Key
  • mezmo.create_view
    Create View
  • mezmo.update_view
    Update Mezmo View
  • mezmo.create_member
    Create Member Invitation
  • mezmo.update_member
    Update Member Role and Groups
  • mezmo.create_category
    Create Category
  • mezmo.update_category
    Update Category
  • mezmo.create_preset_alert
    Create Preset Alert
  • mezmo.update_preset_alert
    Update Preset Alert
  • mezmo.update_index_rate_alert
    Update Index Rate Alert Configuration
  • mezmo.create_ingestion_exclusion
    Create Ingestion Exclusion Rule
  • mezmo.update_ingestion_exclusion
    Update Ingestion Exclusion Rule
  • mezmo.ingest_logs
    Ingest Logs to Mezmo
  • mezmo.resume_ingestion
    Resume Log Ingestion

destructive

7

Delete, cancel or archive. Ask first, or deny outright.

  • mezmo.delete_key
    Delete API Key
  • mezmo.delete_view
    Delete View
  • mezmo.delete_member
    Delete Organization Member
  • mezmo.delete_category
    Delete Category
  • mezmo.delete_preset_alert
    Delete Preset Alert
  • mezmo.delete_pipeline_alert
    Delete Pipeline Alert
  • mezmo.delete_ingestion_exclusion
    Delete Ingestion Exclusion
03 · HOW IT WORKS

Mezmo in three steps.

  1. 01Your users connect MezmoThey add their Mezmo api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create API Key” can wait for the user, and “delete API Key” can be denied outright.
  3. 03Any agent can actYour agent calls Mezmo through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('mezmo', {
  read: 'allow',
  write: 'ask',        // create_key
  destructive: 'deny',  // delete_key
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Mezmo connects.

Users add their Mezmo api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Mezmo connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Mezmo from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Mezmo and Arc0, answered.

Q01

Can I use Mezmo with Claude, ChatGPT or Cursor?

Yes. Connect Mezmo to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Mezmo actions you allow.

Q02

How do users connect Mezmo?

Users add their Mezmo api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Mezmo actions can my agent take?

36 in total: 14 read, 15 write and 7 destructive, such as “create API Key”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Mezmo?

Yes. Actions like “delete API Key” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Mezmo too?

Yes. The same Mezmo connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Mezmo into your agent.

Your users connect Mezmo once, under your brand. Your agent gets 36 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan