Skip to main content
Glama
@yawlabs/tailscale-mcp

@yawlabs/tailscale-mcp

by YawLabs

Set log stream config

tailscale_set_log_stream_config
Idempotent

Configures Tailscale audit or network log streaming by setting the destination, credentials, compression, and upload interval.

Instructions

Set the log streaming configuration for a specific log type. Configures where logs are sent (e.g. Axiom, Datadog, Splunk, Elasticsearch, S3).

Per-destination required fields:

  • splunk / elastic / panther / cribl / datadog / axiom: url + token (user optional)

  • s3: s3Bucket + s3Region + s3AuthenticationType, plus either (s3AccessKeyId + s3SecretAccessKey) for 'accesskey' auth or s3RoleArn for 'rolearn' auth. Call tailscale_create_aws_external_id first when using 'rolearn'.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "logType": "<logType>",
      "destinationType": "<destinationType>"
    },
    "name": "tailscale_set_log_stream_config"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoDestination URL (required for non-s3 destinations; for s3, an optional S3-compatible endpoint)
userNoUsername for the destination (if required)
tokenNoAuthentication token or API key for the destination. SENSITIVE: passed straight to Tailscale and not echoed back, but MCP clients may log the input value you supply.
logTypeYesThe log type: 'configuration' for audit logs, 'network' for network flow logs
s3BucketNo(s3 only) S3 bucket name. Required when destinationType is 's3'.
s3RegionNo(s3 only) AWS region of the S3 bucket. Required when destinationType is 's3'.
s3RoleArnNo(s3 only) IAM role ARN that Tailscale will assume. Required when s3AuthenticationType is 'rolearn'.
s3KeyPrefixNo(s3 only) Optional prefix prepended to the auto-generated S3 object key.
s3AccessKeyIdNo(s3 only) AWS access key id. Required when s3AuthenticationType is 'accesskey'.
destinationTypeYesThe log streaming destination type
compressionFormatNoCompression algorithm for log uploads. Defaults to 'none'.
s3SecretAccessKeyNo(s3 only) AWS secret access key. Required when s3AuthenticationType is 'accesskey'. SENSITIVE: see the token field's note about MCP client logging.
uploadPeriodMinutesNoMinutes to wait between uploads (1-1440). Optional.
s3AuthenticationTypeNo(s3 only) Authentication mode. Required when destinationType is 's3'. Tailscale recommends 'rolearn'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.23.1
    • changedInput schema / properties / url / description
      Previous value: -"Destination URL (required for non-s3 destinations)"New value: +"Destination URL (required for non-s3 destinations; for s3, an optional S3-compatible endpoint)"
  2. First observedv0.13.3

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety and repeatability profile is covered. The description adds one genuinely new behavioral fact — the dependency on tailscale_create_aws_external_id for rolearn auth — but does not say whether an existing config is overwritten, whether log streaming must first be enabled, or what happens on partial failures.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded purpose sentence followed by a compact, scannable bulleted list of per-destination requirements; nothing is padded. The only minor waste is repeating schema-documented 'required when' rules in prose form.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter mutation with no output schema, the description covers the conditional-requirement matrix and the AWS role-creation prerequisite, which are the main failure modes. Gaps remain around overwrite semantics and the post-call state, but no output schema exists so return-value detail is not expected.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every one of the 14 parameters is already documented, including the conditional 'required when' notes for s3 fields. The per-destination bullet list aggregates that information usefully into destination-level groupings, but it is largely a restatement of schema content rather than new meaning, which fits the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Set the log streaming configuration') plus the scoping dimension ('for a specific log type'), and names the concrete destination families. This clearly separates it from the sibling read/delete pair tailscale_get_log_stream_config and tailscale_delete_log_stream_config.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit cross-tool prerequisite ('Call tailscale_create_aws_external_id first when using rolearn') and enumerates which fields each destination requires, which is real when-to-use guidance. It stops short of stating when not to use it (e.g. versus re-running on an already-configured log type) or that the sibling tailscale_validate_aws_trust_policy should precede role-based setup.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools