Item detail
github.com

awslabs/mcp

awslabs/mcp is a developer tool in RepoRadar's AI Infrastructure section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 10.0 out of 10.

Score9.0
Popularity93.0
Riskconditional
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum9.0
Maturity8.9
Open-source/build8.4
Evidence7.2
Workflow potential10.0
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for teams on AWS who need practical MCP integrations without hand-building service-specific glue.

Who should use it

platform engineers standardizing on AWS builders adding tool-calling workflows enterprise teams preferring official AWS integrations

Who should skip it

Move on from awslabs/mcp if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

awslabs/mcp is tracked by RepoRadar as a developer tool in the AI Infrastructure section. It was first seen on 2026-06-17 and last updated on 2026-06-17. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for awslabs/mcp are workflow potential (10.0) and practical usefulness (9.0), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned awslabs/mcp a composite score of 9.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 93.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

AWS credentials are sensitive; strict IAM scoping is required before exposing tools to multi-agent flows.

Evidence links
Closest alternatives / related signals
mcp aws infrastructure agent-tools cloud-ops
Verification record

What RepoRadar actually verified

Tested in a bounded workflow

Bounded representative workflow retained by RepoRadar verification harness. Last checked 2026-07-14T05:27:13.518974Z.

passed · cohort-20260714-aws-documentation-mcp-public-read-workflow

Tester
RepoRadar automated local verification harness
Started
2026-07-14T05:27:08.511703Z
Completed
2026-07-14T05:27:13.518974Z
Environment
Windows 10 AMD64; Python 3.11.9; credential-stripped child environment; disposable home/cache
Install/setup time
1 minute(s)
Evidence scope
Bounded representative workflow
Cleanup
Per-check temporary home and work directory removed. Shared cohort package cache removed.
Actions exercised
  • Created a disposable home, work directory, and isolated package cache with credential-like environment variables excluded.
  • Created 1 synthetic fixture file(s) inside the disposable work directory; retained hashes prove the exact inputs.
  • Installed the pinned AWS Documentation MCP server in an isolated uv environment and spawned its official stdio entrypoint.
  • Negotiated MCP initialization, listed the advertised tools, and invoked read_documentation for AWS's public Amazon S3 overview URL.
  • Validated the returned source URL, expected heading and service marker, then retained a content length and SHA-256 digest rather than copying the page body.
  • Executed bounded check: Start AWS's pinned Documentation MCP server over stdio, negotiate an MCP session, list its tools, and retrieve one public Amazon S3 documentation page through read_documentation.
  • Captured the complete sanitized stdout, stderr, exit status, artifact checks, and 5.01-second wall time.
Observed results
  • Command exited 0 after 5.01 seconds.
  • The official server completed an MCP initialize/list/call sequence and returned the expected public S3 documentation content without AWS credentials.
  • Expected marker 'CHECK_OK server=awslabs.aws-documentation-mcp-server tool=read_documentation marker=true url=true' was observed in retained output.
  • Validated result.json: 5 required marker(s) present and 0 excluded marker(s) absent; size and SHA-256 are retained.
Observed strengths
  • The server exposed a standards-based, machine-readable documentation lookup over local stdio and preserved source attribution in the result.
Friction
  • The tool still depends on live availability of the public AWS documentation page; this run did not cover account-aware or mutating AWS MCP servers.
  • Setup or runtime emitted 18 stderr line(s); the complete warnings/errors are preserved in the retained log.
Limitations
  • This bounded public-document read does not authenticate to AWS, inspect an AWS account, exercise write-capable AWS MCP servers, validate every documentation partition, or measure long-lived server reliability.
  • This credential-free disposable workflow does not establish operator use, production scale, model quality, reliability under sustained use, or team adoption.

Pricing assessment: The open-source MCP server and public AWS documentation read used no AWS account, cloud resource, paid API, or model provider.

Privacy assessment: Only a public AWS documentation URL was sent to docs.aws.amazon.com; no repository content, user data, AWS credential, account identifier, or prompt was transmitted.

Open retained test log →

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

38 dated snapshots retained from 2026-06-17 through 2026-08-03; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score9.0 current · +0.0 net
Repository momentum9.3 current · +0.3 net
GitHub stars (observed)9,541 current · +103 net
GitHub stars9,541 exact observation
Version2026.07.20260728181317
Last release2026-07-28T19:47:32Z
Maintenanceactive
Current riskconditional
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineAWS

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-039.09.39,541conditionaltry nowactive
2026-08-029.09.39,531conditionaltry nowactive
2026-08-019.09.09,527conditionaltry nowactive
2026-07-319.09.0Not recordedconditionaltry nownot recorded
2026-07-309.09.0Not recordedconditionaltry nownot recorded
2026-07-299.09.39,512conditionaltry nowactive
2026-07-289.09.09,510conditionaltry nowactive
2026-07-219.09.09,458conditionaltry nowactive
2026-07-209.09.09,458conditionaltry nowactive
2026-07-199.09.09,458conditionaltry nowactive
2026-07-189.09.09,458conditionaltry nowactive
2026-07-179.09.09,458conditionaltry nowactive

Why the record changed

stars changed

Stars changed: 9531 → 9541.

stars changed

Stars changed: 9527 → 9531.

stars changed

Source-observed stars changed: 9525 → 9527. This reports the retained observation delta and does not infer why the upstream change occurred.

stars changed

Stars changed: 9510 → 9512.

version changed

Version changed: 2026.07.20260723053753 → 2026.07.20260728181317.

stars changed

Stars changed: 9458 → 9510.

version changed

Version changed: 2026.07.20260713210810 → 2026.07.20260723053753.

stars changed

Stars changed: 9438 → 9458.

verification changed

Verification changed: Discovered → Tested in a bounded workflow.