Skip to main content
Glama

Second Wind AI

cross account pipeline artifact denied

codepipeline-cross-account-artifact-access
Read-onlyIdempotent

Send the pipeline definition plus the artifact bucket policy, artifact key policy and the roles involved. Checks every cross account action for the seven things that must line up across both accounts: Regional artifact store, customer managed key named by ARN, key policy, bucket policy, action role permissions, trust, and the pipeline role's permission to assume. Returns each failing item with the generated statement or pipeline change. Use when the error reads: Access Denied (Service: Amazon S3) in a cross account action | The ciphertext refers to a customer master key that does not exist | is not authorized to perform: sts:AssumeRole on resource: | Insufficient permissions: unable to access the artifact. Covers: Pipelines with S3 artifact stores and actions that name a roleArn in another account. Evaluates supplied policies only. Does not check the deployment's own permissions inside the target account. Price: 8.00 USDC on Base via x402, charged only when the case is solved.

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": {
      "pipeline": "<pipeline>",
      "pipeline_account_id": "<pipeline_account_id>",
      "pipeline_region": "<pipeline_region>"
    },
    "name": "codepipeline-cross-account-artifact-access"
  }
}

Input Schema

NameRequiredDescriptionDefault
rolesNoKeyed by role ARN: the pipeline role (identity_policies) and each cross account action role (trust_policy and identity_policies).
kms_keysNoArtifact keys keyed by the encryptionKey id used in the pipeline.
pipelineYesThe pipeline object from aws codepipeline get-pipeline --name NAME.
error_messageNo
failing_actionNoName of the action that fails. Omit to check every cross account action.
bucket_policiesNoArtifact bucket policies keyed by bucket name.
pipeline_regionYes
pipeline_account_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so the safety profile is covered; the description adds scope limits (supplied policies only, target-account deployment permissions excluded) and a billing trait ('8.00 USDC on Base via x402, charged only when the case is solved') that an agent cannot infer from structured fields. It also sketches the return shape ('Returns each failing item with the generated statement or pipeline change'). It does not say how many actions are checked or what happens when inputs are incomplete, so it stops short of a 5.

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 with the action to take ('Send the pipeline definition plus ...'), then the checks, then the error triggers, then scope. Dense and mostly waste-free, though the four-way pipe-separated error list plus a separate 'Covers:' sentence repeats scope information and could be tightened.

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 an 8-parameter tool with nested policy objects and no output schema, the description supplies the return shape, the evaluation boundary, and the failure triggers, which is most of what an agent needs. The remaining gap is per-parameter guidance for the optional error_message and failing_action inputs, and it does not say what the response looks like when all seven checks pass.

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

Parameters4/5

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

Schema description coverage is 63%, and the description meaningfully names the inputs to supply: the pipeline definition, artifact bucket policy, artifact key policy, and the roles involved — mapping onto pipeline, bucket_policies, kms_keys and roles. 'Across both accounts' and 'Regional artifact store' implicitly flag pipeline_account_id and pipeline_region, but error_message and failing_action are never mentioned in prose, leaving part of the coverage gap unfilled.

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: it checks every cross account action for 'the seven things that must line up across both accounts' (artifact store, CMK by ARN, key policy, bucket policy, action role permissions, trust, pipeline role assume). That enumeration makes the scope unmistakable and distinguishes it from the sibling tools, which all target different AWS failure domains (EventBridge, IAM layers, CDK, CloudFormation, Lambda, security groups).

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

Usage Guidelines5/5

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

Gives concrete trigger strings ('Access Denied (Service: Amazon S3)', 'The ciphertext refers to a customer master key that does not exist', 'is not authorized to perform: sts:AssumeRole on resource: <action role>') so the agent can pattern-match an error to this tool. It also states the coverage envelope ('Pipelines with S3 artifact stores and actions that name a roleArn in another account') and an explicit exclusion ('Does not check the deployment's own permissions inside the target account'), which is exactly the when-not guidance needed.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources