AWS Data Processing MCP Server (AWS Labs)
Capped at 70: no passing tool call yet; the tests add up to 100. Why scores are capped
Test points add up to 100; the score is capped at 70 until a tool call passes. Not a quality or security rating. Methodology
Test points before the cap (100/100)
- Install20/20
- Handshake30/30
- Maintenance25/25
- Docs15/15
- License10/10
Tested pypi awslabs-aws-dataprocessing-mcp-server 0.2.3 (Apache-2.0; repo awslabs/mcp). Installed pinned with scripts off (uv venv, Python 3.13) and launched: initialize and tools/list over stdio succeeded with no credentials and listed 36 tools (no tool annotations). Real calls: 0 of 3 real function calls passed. Calls need AWS credentials. Core tools not tested: 70 cap. Capture used a retry: 120 s handshake timeout (first pass timed out at 45 s).
Tool-call test (2026-11-13 UTC, direct MCP stdio client, no LLM): fail. 0 of 3 real function calls passed. Calls need AWS credentials. Evidence: local test run, Nov 13, 2026 UTC.
Transport (tested 2026-11-13 UTC): stdio
Token cost (estimate): approx. 30283 tokens, cl100k estimate (36 tools, measured 2026-11-13 UTC, version 0.2.3). This is an estimate from our testing of the tool names, descriptions and input schemas, counted with cl100k_base.
Permissions: 4 read, 25 write (state-changing), 7 unclassified · Auth: API key · Rate limit: unknown · Pricing unit: unknown
Auth: API key. Rate limit: unknown. Pricing unit: unknown.
add_inline_policy— write (state-changing)analyze_s3_usage_for_data_processing— unclassifiedcreate_data_processing_role— write (state-changing)get_policies_for_role— readget_roles_for_service— readlist_s3_buckets— readmanage_aws_athena_data_catalogs— write (state-changing)manage_aws_athena_databases_and_tables— readmanage_aws_athena_named_queries— write (state-changing)manage_aws_athena_query_executions— write (state-changing)manage_aws_athena_workgroups— write (state-changing)manage_aws_emr_clusters— write (state-changing)manage_aws_emr_ec2_instances— unclassifiedmanage_aws_emr_ec2_steps— unclassifiedmanage_aws_emr_serverless_applications— write (state-changing)manage_aws_emr_serverless_job_runs— unclassifiedmanage_aws_glue_catalog— write (state-changing)manage_aws_glue_classifiers— write (state-changing)manage_aws_glue_connection_metadata— unclassifiedmanage_aws_glue_connection_types— unclassifiedmanage_aws_glue_connections— write (state-changing)manage_aws_glue_crawler_management— write (state-changing)manage_aws_glue_crawlers— write (state-changing)manage_aws_glue_databases— write (state-changing)manage_aws_glue_encryption— write (state-changing)manage_aws_glue_jobs— write (state-changing)manage_aws_glue_partitions— write (state-changing)manage_aws_glue_resource_policies— write (state-changing)manage_aws_glue_security_configurations— write (state-changing)manage_aws_glue_sessions— write (state-changing)manage_aws_glue_statements— unclassifiedmanage_aws_glue_tables— write (state-changing)manage_aws_glue_triggers— write (state-changing)manage_aws_glue_usage_profiles— write (state-changing)manage_aws_glue_workflows— write (state-changing)upload_to_s3— write (state-changing)
listing-flags calls_need_key or auth_kind
Score 70/100 · Tools 36 · Token cost approx. 30,283 tokens · Compare · Last tested 2026-11-13 UTC · Version tested 0.2.3 · Package awslabs-aws-dataprocessing-mcp-server · Repo awslabs/mcp
Summary: AWS Data Processing MCP Server (AWS Labs) completed an MCP handshake without credentials and exposed 36 tools.
Evidence summary
- Handshake
- pass
- Tools listed
- 36
- Context cost
- approx. 30283 tokens, cl100k estimate (36 tools, measured 2026-11-13 UTC, version 0.2.3; an estimate) ranking · add up your servers' context cost
- API key
- Connects without a key; tool calls need one
- Tested
- 2026-11-13 UTC
Test results
| Test | Result | Points | Evidence |
|---|---|---|---|
| install | pass | 20 | uv pip install awslabs-aws-dataprocessing-mcp-server (Python venv, Linux) succeeded in 0s. |
| handshake | pass | 30 | MCP initialize + tools/list over stdio succeeded with no credentials; 36 tools listed in 38.0s. |
| maintenance | pass | 25 | Repo pushed 0 days before test; 9,913 GitHub stars. |
| docs | pass | 15 | README over 3,000 chars; install instructions present; mcpServers config example present. Check of the package's own README (PyPI long_description (package README)). |
| license | pass | 10 | Apache-2.0 (OSI-approved). |
Local-model readiness
Token cost (estimate): approx. 30283 tokens, cl100k estimate for 36 tools · about 370% of an 8k context. This is an estimate from our testing (counted with cl100k_base).
Small-model friendly (schema heuristic, not a model result): unknown.
Not tested
Small-model task runs: Not yet tested.
What we tested and what we didn't
Tested on 2026-11-13 UTC
- Install from the registry
- We connected with no credentials and asked for its tool list: it listed 36 tools (Method details: MCP
initializethentools/list) - Maintenance signals (last push, archived/deprecated status)
- Docs (README length, install and config example)
- License (OSI-approved or not)
- Token cost (estimate)
Not tested
- Security: not audited (no code review, no permission or data-flow analysis)
- Real tasks (no functional task runs yet)
- Behaviour with real credentials or a real account
- Performance, rate limits or load
- Correctness of results beyond the listed tasks
Methodology: how we test. A high score means it installs and responds, not that giving it access to your data carries no risk.
Known security issues
Not yet checked.
Monthly roundup: MCP security issues, October 2026.
Tool list changes
Baseline recorded from the 2026-11-13 UTC test run; changes appear after the next test.
Snapshot hash (fingerprint of the tool list)
822ae4177f8b: SHA-256 of the canonical tool names, descriptions and input schemas. If it changes, the tool list changed.
Raw test record (JSON)
{
"name": "awslabs-aws-dataprocessing-mcp-server",
"version": "0.2.3",
"registry": "pypi",
"status": "working",
"tested": "2026-11-13",
"tools_count": 36,
"deprecated": false,
"archived": false,
"tests": {
"install": [
"pass",
20,
"`uv pip install awslabs-aws-dataprocessing-mcp-server` (Python venv, Linux) succeeded in 0s."
],
"handshake": [
"pass",
30,
"MCP `initialize` + `tools/list` over stdio succeeded with no credentials; 36 tools listed in 38.0s."
],
"maintenance": [
"pass",
25,
"Repo pushed 0 days before test; 9,913 GitHub stars."
],
"docs": [
"pass",
15,
"README over 3,000 chars; install instructions present; `mcpServers` config example present. Check of the package's own README (PyPI long_description (package README))."
],
"license": [
"pass",
10,
"Apache-2.0 (OSI-approved)."
]
}
}Install
uvx awslabs-aws-dataprocessing-mcp-server
Pin the version we tested
uvx --from awslabs-aws-dataprocessing-mcp-server==0.2.3 awslabs.aws-dataprocessing-mcp-server
pip install awslabs-aws-dataprocessing-mcp-server==0.2.3
tested 2026-11-13 UTC. Newer versions may differ and were not tested by us.
{
"mcpServers": {
"aws-data-processing-mcp-server-aws-labs": {
"command": "uvx",
"args": [
"--from",
"awslabs-aws-dataprocessing-mcp-server==0.2.3",
"awslabs.aws-dataprocessing-mcp-server"
]
}
}
}Tools listed
manage_aws_glue_databases, manage_aws_glue_tables, manage_aws_glue_connections, manage_aws_glue_connection_types, manage_aws_glue_connection_metadata, manage_aws_glue_partitions, manage_aws_glue_catalog, manage_aws_glue_sessions, manage_aws_glue_statements, manage_aws_glue_workflows, manage_aws_glue_triggers, manage_aws_glue_jobs, manage_aws_glue_usage_profiles, manage_aws_glue_security_configurations, manage_aws_glue_encryption, manage_aws_glue_resource_policies, manage_aws_athena_query_executions, manage_aws_athena_named_queries, manage_aws_athena_data_catalogs, manage_aws_athena_databases_and_tables, manage_aws_athena_workgroups, manage_aws_glue_crawlers, manage_aws_glue_classifiers, manage_aws_glue_crawler_management, manage_aws_emr_clusters, manage_aws_emr_ec2_steps, manage_aws_emr_ec2_instances, manage_aws_emr_serverless_applications, manage_aws_emr_serverless_job_runs, add_inline_policy, get_policies_for_role, create_data_processing_role, get_roles_for_service, list_s3_buckets, upload_to_s3, analyze_s3_usage_for_data_processing
Quick config
{
"mcpServers": {
"aws-data-processing-mcp-server-aws-labs": {
"command": "uvx",
"args": [
"awslabs-aws-dataprocessing-mcp-server"
]
}
}
}Add to config Opens the config generator with this server selected.
Setup
- Install. Run
uv pip install awslabs-aws-dataprocessing-mcp-server(Python venv). This is the exact command we ran on 2026-11-13 UTC. - Configure. Add the mcpServers entry below to your MCP client config.
- Verify. Restart the client and check that tools/list returns tools (36 in our test).
{
"mcpServers": {
"aws-data-processing-mcp-server-aws-labs": {
"command": "uvx",
"args": [
"awslabs-aws-dataprocessing-mcp-server"
]
}
}
}Test history
- 2026-11-13 UTC: New
Related: Best cloud MCP servers
FAQ
Is AWS Data Processing MCP Server (AWS Labs) deprecated?
No. awslabs-aws-dataprocessing-mcp-server was not deprecated or archived when we last tested it on 2026-11-13 UTC.
What replaces AWS Data Processing MCP Server (AWS Labs)?
Nothing; AWS Data Processing MCP Server (AWS Labs) is not deprecated as of 2026-11-13 UTC.
Does AWS Data Processing MCP Server (AWS Labs) need an API key?
It connects and lists 36 tools without a key, but its tool calls need one.
Embed the badge
Every tested server gets a free embeddable badge. It shows the current score and test date and expires after 90 days. Testing is free; payment never changes a score.