Integration

Mezmo integration

Mezmo (formerly LogDNA) log management: list, read and delete boards, list, read, create and delete screens (dashboards of log graphs and widgets), manage ingestion exclusion rules (which log lines are not stored or not indexed), list, read and delete custom parsing templates, report storage usage by app or tag over a period, check whether the account is ingesting, summarize Telemetry Pipeline ingestion and source health, and read Mezmo AI SRE investigations. Each tool needs the access token to hold the permission it names (such as board read). Not exposed: log export and search (log lines can carry any data), log ingestion (separate ingestion key), views, alerts, categories and groups (the spec does not describe their answers), pipeline building and editing, ingestion suspension, archiving (cloud storage credentials), keys, members, users, roles, service accounts, access tokens and enterprise accounts, usage by host, and board creation (its answer is not described). Authentication: a Mezmo IAM access token sent as Authorization: Token <token>.

Connect Mezmo How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Mezmo.Built from the 23 Mezmo tools below, on the connection you add once.

What you can do with Mezmo

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Exclusion rule, 5 operations

create_exclusionCreate exclusionPOSTCreates an exclusion rule, for real: once active, matching new log lines are no longer stored (or only not indexed). Needs the exclusion write permission.
delete_exclusionDelete exclusionDELETEDeletes an exclusion rule, for real, so matching lines are stored again. Needs the exclusion manage permission.
get_exclusionGet exclusionGETReturns one exclusion rule, as a one-element list. Needs the exclusion read permission.
list_exclusionsList exclusionsGETLists the ingestion exclusion rules (not the usage quota rules): title, hosts, apps, query, active, indexonly. Needs the exclusion read permission.
update_exclusionUpdate exclusionPATCHChanges an exclusion rule, for real (it can start or stop dropping log lines). Needs exclusion write. The vendor requires title: read the rule with get_exclusion first.

Screen, 4 operations

create_screenCreate screenPOSTCreates a screen visible to the whole account, for real, and returns it with its id. Needs the screen write permission.
delete_screenDelete screenDELETEDeletes a screen for everyone on the account, for real. Needs the screen manage permission.
get_screenGet screenGETReturns one screen: title, aspect ratio, rotation, background, categories and every widget with its type, operation, field, filter, position and options. Needs screen read.
list_screensList screensGETLists the screens of the account in short form (id, account, title). Needs the screen read permission.

Board, 3 operations

delete_boardDelete boardDELETEDeletes a board for everyone on the account, for real. Needs the board manage permission.
get_boardGet boardGETReturns one board: title, graphs, their order and categories. Needs the board read permission.
list_boardsList boardsGETLists the boards of the account (id, account, title). Needs the board read permission.

Parsing template, 3 operations

delete_parsing_templateDelete parsing templateDELETEDeletes a custom parsing template, for real, so new lines are no longer parsed by it. Needs the custom_parsing manage permission.
get_parsing_templateGet parsing templateGETReturns one custom parsing template: priority, draft and active flags, query and its top-level parsing operators. Needs the custom_parsing read permission.
list_parsing_templatesList parsing templatesGETLists the custom parsing templates of the account (templateid, account, name). Needs the custom_parsing read permission.

Ai investigation, 2 operations

get_ai_investigationGet ai investigationGETReturns one Mezmo AI SRE investigation: trigger source, linked alert, evidence, confidence score, suggested resolution, resolution status and state.
list_ai_investigationsList ai investigationsGETLists the Mezmo AI SRE investigations of the account: trigger, linked alert, evidence, confidence, suggested resolution, state. Page with last_id.

App usage, 2 operations

get_app_usageGet app usageGETReturns the storage one app used over a period, in bytes on disk; results holds one item, or none when the app had no data. Needs the log read permission.
list_app_usageList app usageGETLists the storage used by each app over a period, in bytes of log lines on disk, by whole days. Needs the log read permission.

Tag usage, 2 operations

get_tag_usageGet tag usageGETReturns the storage one tag used over a period, in bytes on disk; results holds one item, or none when the tag had no data. Needs the log read permission.
list_tag_usageList tag usageGETLists the storage used by each tag over a period, in bytes of log lines on disk, by whole days. Needs the log read permission.

Ingestion status, 1 operation

get_ingestion_statusGet ingestion statusGETTells whether the account is currently ingesting log data (false while ingestion is suspended). Needs the log read permission.

Pipeline health, 1 operation

get_pipeline_healthGet pipeline healthGETSummarizes Telemetry Pipeline health: status code changes per ingestion route, and per published pipeline its sources and their consumer lag.

Use Mezmo from Claude Code, Cursor or Codex

Connect Mezmo in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Mezmo operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Mezmo

Create your workspace
Sign up free. Nothing to install.
Connect Mezmo once
Add your Mezmo connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.