Public record
Software health reportschema 0.31.0 · metrics 2.10.0 · 2026-08-06 00:04 UTC

thomaswitt / mcp-agents

MCP server that wraps the Claude Code and Gemini CLI so any MCP client (e.g. codex) can call it as a tool.

JavaScript · ShellNo license detected★ 7 stars⑂ 2 forkssince Feb 2026View on GitHub ↗
KindCommand-line toolMCP serverLibraryhow this is determined

thomaswitt/mcp-agents holds a health index of 45 out of 100, placing it in the Weak band. It scores highest on Vitality (75/100) and lowest on Engineering Quality (27/100). It was last updated 11 days ago. A single contributor accounts for most of its recent work.

45
overall / 100
Weak

Software health index

Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.

45
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
VitalityCommunity &AdoptionSustainability &GovernanceEngineeringQualitySecurityAI Readiness

Score profile

Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.

The weighted overall 47 is calibrated to 45 on the published index scale (record calibration 2026-08-02).

Ownership

Thomas WittPersonal account
37 followers21 public repossince Jan 2009@vendis-ai

This repository is owned by a personal account. A single-owner project carries more continuity risk than an organization-backed one.

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
npmmcp-agents0.25.02,8044111 days agomcpclaudegeminicodexanthropicgoogleopenaiaicli

Metrics by category

Vitality

Is the project alive — is code being written and are releases shipping?

75Good · 21% of overall

Development activity

66Good
How it's scored
28.8/36Push recency — last push 11 days ago
11.1/36Commit cadence — 16/52 weeks with commits
15.8/18Commit volume — 56 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year56
human_commit_share1
days_since_last_push11
active_weeks_last_year16

Release discipline

88Excellent
How it's scored
16.2/27Ships releases — 40 version tags (no GitHub releases)
36/36Release recency — latest release 11 days ago
27/27Release cadence — a release every ~1.4 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count40
latest_release_tagv0.24.0
releases_from_tagsyes
days_since_latest_release11
mean_days_between_releases1.4
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

28At Risk · 17% of overall

Popularity & adoption

13Critical
How it's scored
12.6/60Stars — 7 stars
0/25Forks — 2 forks
0/15Watchers — 0 watchers
Inputs used
forks2
stars7
watchers0
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

25At Risk
How it's scored
22.5/22.5README
0/22.5License — no license file detected
0/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseno
readme_badges0
has_contributingno
has_issue_templateno
has_code_of_conductno
readme_badge_services—
has_pull_request_templateno

Ecosystem adoption (downloads)

58Moderate
How it's scored
46/80Monthly downloads — 2,804 downloads/month across npm
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesmcp-agents
dependents—
ecosystemsnpm
total_downloads—
monthly_downloads2,804
unverified_packages_excluded—
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.

Sustainability & Governance

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?

55Moderate · 23% of overall

Maintainer resilience (bus factor)

16Critical
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
0.8/22.5Commit distribution — top contributor authored 96% of commits
2.7/13.5Contributor breadth — 2 contributors
3/10OpenSSF Scorecard: Contributors — project has 1 contributing companies or organizations -- score normalized to 3
Inputs used
bus_factor1
contributors_sampled2
top_contributor_share0.964

Issue & PR responsiveness

67Good
How it's scored
0/42Issue resolution — no issues or no data
30/30PR acceptance — 2/2 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
0/15OpenSSF Scorecard: Code-Review — Found 1/28 approved changesets -- score normalized to 0
Inputs used
merged_prs2
open_issues0
closed_issues0
prs_merged_7d0
prs_decided_7d0
prs_merged_30d1
prs_decided_30d1
issue_closed_ratio—
closed_unmerged_prs0
first_time_authors_30d0
first_time_prs_merged_30d0
first_time_prs_decided_30d0
Excluded from scoring (no data or not applicable): Issue resolution, Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

54Moderate
How it's scored
10/30Ownership backing — personal (user) account
0/20Verified domain — not applicable to user accounts
11.4/25Owner reach — 37 followers of thomaswitt
21.8/25Track record — 21 public repos, account ~17 yr old
Inputs used
followers37
owner_typeUser
is_verified—
owner_loginthomaswitt
public_repos21
account_age_days6,411
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on npm
35/35Publish recency — latest publish 11 days ago
20/20Version history — 41 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesmcp-agents
ecosystemsnpm
any_deprecatedno
min_days_since_publish11

Engineering Quality

Are baseline engineering and documentation practices in place?

27At Risk · 19% of overall

Engineering practices

1Critical
How it's scored
0/24CI workflows
0/24Tests present
0/16Linter config
0/9.6Pre-commit hooks
0/6.4.editorconfig
0/20OpenSSF Scorecard: CI-Tests — 0 out of 1 merged PRs checked by a CI test -- score normalized to 0
Inputs used
has_cino
has_testsno
has_editorconfigno
has_linter_configno
has_precommit_configno

Documentation

65Good
How it's scored
30/30README
0/25Documentation directory
15/15Documentation / homepage site — https://www.npmjs.com/package/mcp-agents
10/10Repository description
0/10Topics
10/10Wiki
Inputs used
topics—
has_wikiyes
homepagehttps://www.npmjs.com/package/mcp-agents
docs_sitehttps://www.npmjs.com/package/mcp-agents
has_readmeyes
has_docs_dirno
has_descriptionyes

Security

Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?

42Weak · 16% of overall

Security posture

27At Risk
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — branch protection not enabled on development/release branches
0/2.5CI-Tests — 0 out of 1 merged PRs checked by a CI test -- score normalized to 0
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 1/28 approved changesets -- score normalized to 0
0.8/2.5Contributors — project has 1 contributing companies or organizations -- score normalized to 3
0/10Dangerous-Workflow — no data
0/7.5Dependency-Update-Tool — no update tool detected
0/5Fuzzing — project is not fuzzed
0/2.5License — license file not detected
7.5/7.5Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
0/5Packaging — no data
0/5Pinned-Dependencies — no data
0/5SAST — SAST tool is not run on all commits -- score normalized to 0
0/5Security-Policy — security policy file not detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — no data
3/7.5Vulnerabilities — 6 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated13
scorecard_versionv5.5.0
checks_inconclusive5
scorecard_aggregate2.7
Excluded from scoring (no data or not applicable): Dangerous-Workflow, Packaging, Pinned-Dependencies, Signed-Releases, Token-Permissions. Remaining weights renormalized.

Dependency advisories

100Exceptional
How it's scored
35/35Direct dependencies free of known advisories — no direct dependency carries a known advisory
25/25Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
0/40No advisories left outstanding — no advisory carries a publication date
Inputs used
sourceosv
advisories0
affected_packages0
assessed_packages95
unassessed_packages0
affected_by_severitynone
direct_affected_packages0
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:mcp-agents@0.25.0 runtime dependency closure — what installing the published package pulls in — 95 packages. Reachability is not analyzed.

AI Readiness

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.

39Weak · 4% of overall

Agent context & guidance

85Excellent
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 48 of 56 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share0.857
agent_instruction_filesAGENTS.md, CLAUDE.md
agent_instruction_max_bytes11,876

Verify loop (build / test / typecheck)

11Critical
How it's scored
0/18One-command bootstrap
0/22Automated tests
0/11Lint / format config
0/11Static type checking
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 56
0/8Automated maintenance — no automated dependency updates observed
0/10OpenSSF Scorecard: Pinned-Dependencies — no data
Inputs used
has_nixno
has_testsno
lockfilespackage-lock.json
has_dockerfileno
typed_languageno
bootstrap_files—
has_devcontainerno
has_linter_configno
typecheck_configs—
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Pinned-Dependencies. Remaining weights renormalized.

Code legibility for models

28At Risk
How it's scored
0/45Type-checkable code — JavaScript without a type-check config
27.5/55Manageable file sizes — 1/2 source files over 60KB
Inputs used
primary_languageJavaScript
largest_source_bytes217,353
source_files_sampled2
oversized_source_files1

Machine-readable interfaces

33At Risk
How it's scored
0/40API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software
20/20MCP server
0/40Runnable examples
Inputs used
example_dirs—
has_mcp_signalyes
api_schema_files—
interfaces_expected_of—
Excluded from scoring (no data or not applicable): API schema (OpenAPI/GraphQL/proto). Remaining weights renormalized.

Key facts

7GitHub stars
2contributors
56commits, last 12 months
11days since last push
40releases
1bus factor
0open issues
npmpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token

More detail

Star and fork history 0 ★ / 2 ⇿
0Stars
2Forks
14Releases

When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.

111222212026-022026-042026-06
Major 0Minor 5Patch 9
OpenSSF Scorecard 2.7 / 10
2.7aggregate

Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).Scorecard v5.5.0 · 2026-08-06 00:04 UTC

10Binary-Artifactsno binaries found in the repo
0Branch-Protectionbranch protection not enabled on development/release branches
0CI-Tests0 out of 1 merged PRs checked by a CI test -- score normalized to 0
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 1/28 approved changesets -- score normalized to 0
3Contributorsproject has 1 contributing companies or organizations -- score normalized to 3
n/aDangerous-Workflowno workflows found
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
0Licenselicense file not detected
10Maintained30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
n/aPackagingpackaging workflow not detected
n/aPinned-Dependenciesno dependencies found
0SASTSAST tool is not run on all commits -- score normalized to 0
0Security-Policysecurity policy file not detected
n/aSigned-Releasesno releases found
n/aToken-PermissionsNo tokens found
4Vulnerabilities6 existing vulnerabilities detected
Direct dependencies 1
RegistryPackageVersion constraintManifest
npm@modelcontextprotocol/sdk^1.24.3package.json
All dependencies 92

Full resolved dependency set from the GitHub dependency graph: 1 direct and 91 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
npm@modelcontextprotocol/sdk1.29.0direct
npm@hono/node-server1.19.15indirect
npmaccepts2.0.0indirect
npmajv8.18.0indirect
npmajv-formats3.0.1indirect
npmbody-parser2.3.0indirect
npmbytes3.1.2indirect
npmcall-bind-apply-helpers1.0.2indirect
npmcall-bound1.0.4indirect
npmcontent-disposition1.1.0indirect
npmcontent-type1.0.5indirect
npmcontent-type2.0.0indirect
npmcookie0.7.2indirect
npmcookie-signature1.2.2indirect
npmcors2.8.6indirect
npmcross-spawn7.0.6indirect
npmdebug4.4.3indirect
npmdepd2.0.0indirect
npmdunder-proto1.0.1indirect
npmee-first1.1.1indirect
npmencodeurl2.0.0indirect
npmes-define-property1.0.1indirect
npmes-errors1.3.0indirect
npmes-object-atoms1.1.2indirect
npmescape-html1.0.3indirect
npmetag1.8.1indirect
npmeventsource3.0.7indirect
npmeventsource-parser3.0.6indirect
npmexpress5.2.1indirect
npmexpress-rate-limit8.6.0indirect
npmfast-deep-equal3.1.3indirect
npmfast-uri3.1.4indirect
npmfinalhandler2.1.1indirect
npmforwarded0.2.0indirect
npmfresh2.0.0indirect
npmfunction-bind1.1.2indirect
npmget-intrinsic1.3.0indirect
npmget-proto1.0.1indirect
npmgopd1.2.0indirect
npmhas-symbols1.1.0indirect
npmhasown2.0.4indirect
npmhono4.12.31indirect
npmhttp-errors2.0.1indirect
npmiconv-lite0.7.3indirect
npminherits2.0.4indirect
npmip-address10.2.0indirect
npmipaddr.js1.9.1indirect
npmis-promise4.0.0indirect
npmisexe2.0.0indirect
npmjose6.1.3indirect
npmjson-schema-traverse1.0.0indirect
npmjson-schema-typed8.0.2indirect
npmmath-intrinsics1.1.0indirect
npmmedia-typer1.1.1indirect
npmmerge-descriptors2.0.0indirect
npmmime-db1.54.0indirect
npmmime-types3.0.2indirect
npmms2.1.3indirect
npmnegotiator1.0.0indirect
npmobject-assign4.1.1indirect
npmobject-inspect1.13.4indirect
npmon-finished2.4.1indirect
npmonce1.4.0indirect
npmparseurl1.3.3indirect
npmpath-key3.1.1indirect
npmpath-to-regexp8.4.2indirect
npmpkce-challenge5.0.1indirect
npmproxy-addr2.0.7indirect
npmqs6.15.3indirect
npmrange-parser1.3.0indirect
npmraw-body3.0.2indirect
npmrequire-from-string2.0.2indirect
npmrouter2.2.0indirect
npmsafer-buffer2.1.2indirect
npmsend1.2.1indirect
npmserve-static2.2.1indirect
npmsetprototypeof1.2.0indirect
npmshebang-command2.0.0indirect
npmshebang-regex3.0.0indirect
npmside-channel1.1.1indirect
npmside-channel-list1.0.1indirect
npmside-channel-map1.0.1indirect
npmside-channel-weakmap1.0.2indirect
npmstatuses2.0.2indirect
npmtoidentifier1.0.1indirect
npmtype-is2.1.0indirect
npmunpipe1.0.0indirect
npmvary1.1.2indirect
npmwhich2.0.2indirect
npmwrappy1.0.2indirect
npmzod4.3.6indirect
npmzod-to-json-schema3.25.1indirect
Dependency advisories 0

Installing npm:mcp-agents@0.25.0 pulls in 95 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.

No known advisories affect the assessed dependencies.

An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.

Raw JSON report machine-readable

Feedback

Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.

The message is kept through sign-in.

Related records

Inspected repositories sharing catalogue tags or ecosystems with thomaswitt/mcp-agents. Read them side by side →

96vercel/aiThe AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents Exceptional98awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessionsExceptional97strands-agents/harness-sdkBuild an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.Exceptional97langgenius/difyBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.Exceptional96Kilo-Org/kilocodeKilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.Exceptional96AstrBotDevs/AstrBotAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨Exceptional

Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.

Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.31.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statistics — npm.