Mezmo MCP server

What the model can do

Mezmo log analysis (formerly LogDNA): search log lines over a time window by query, host, app and level, saved views and their alert triggers, preset alerts, boards, storage usage by app, host and tag, exclusion rules and whether logs are being ingested; when you ask, can create or delete a view, create or delete an email alert, create, switch or delete an exclusion rule, resume ingestion, and invite or remove a member.

Reads

• mezmo_search_logsLog lines from Mezmo in a time window, filtered by search query, hosts, apps and levels: the newest lines first by default (oldest with oldest_first).
• mezmo_list_viewsSaved views: name, query, hosts, apps, levels, tags and categories, and the kind and trigger of any alerts on them (never their addresses or URLs).
• mezmo_list_alertsPreset alerts (reusable alerts attached to views): name and, per channel, its kind (email, Slack, PagerDuty, webhook), presence or absence…
• mezmo_list_boardsDashboards (boards) in the Mezmo organization, by id and title.
• mezmo_usageLog storage used in a period: account totals (plan, restored and variable-retention bytes) and, with by set, the top apps, hosts or tags by bytes.
• mezmo_ingestionWhether the Mezmo organization is ingesting logs now, and its exclusion rules (which matching lines are dropped before storage).

Acts, when you ask

These change something in Mezmo. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

• mezmo_create_viewSaves a view in Mezmo (a named query with host, app, level and tag filters) that everyone in the organization can open…
• mezmo_delete_viewDeletes a saved view and the alerts attached to it, for everyone in the organization; the alerts stop.
• mezmo_create_email_alertCreates a preset alert in Mezmo that emails the addresses given when lines match (presence) or stop arriving…
• mezmo_delete_alertDeletes a preset alert; every view it is attached to stops alerting through it.
• mezmo_create_exclusionCreates an exclusion rule: new log lines matching its hosts, apps and query are dropped at ingest, not stored and not counted toward storage.
• mezmo_update_exclusionChanges an exclusion rule (switch it off with active false so lines are stored again, or on, or change its filters); only the fields passed change.
• mezmo_delete_exclusionDeletes an exclusion rule, so lines it dropped are stored again from now on (and count toward usage).
• mezmo_resume_ingestionResumes log ingestion for the whole Mezmo organization after it was suspended, so logs are stored (and count toward usage) again.
• mezmo_invite_memberInvites a person to the Mezmo organization by email with a role (readonly, member, admin or owner), which emails them an invitation and…
• mezmo_remove_memberRemoves a member from the Mezmo organization by email, ending their access to its logs at once.

Connect it

First connect Mezmo on Dashboard → Connections, then add Memtro to your client once. The Mezmo tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Mezmo connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

• › How many checkout errors were logged in the last hour?
• › Show the latest error lines from the payments app.
• › Which apps used the most log storage last week?
• › Are we ingesting logs right now?
• › Switch off the health check exclusion rule.

Questions

Is this an official Mezmo MCP server?

No. It is Memtro's MCP server with Memtro's Mezmo connector behind it: the connector reads Mezmo through its API with the credentials you connect on Dashboard → Connections, and Mezmo publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

What does it cost?

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Mezmo?

Only when you ask, and only what it has been granted: create a saved view, optionally with an email alert; delete a saved view and its alerts; create a preset email alert; delete a preset alert; create an exclusion rule that stops matching lines being stored; switch an exclusion rule on or off, or change it; delete an exclusion rule; resume log ingestion after a suspension; invite a member to the organization with a role; remove a member from the organization. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Which clients work?

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Engineering and operations

• GitHub MCP server
• AWS CloudWatch MCP server
• Sentry MCP server
• ServiceNow MCP server
• Okta MCP server
• Twilio MCP server