inventory_resumes_resumes_portfolio_link_audit_track
Count the portfolio link audit item collection by category. Returns spend, quantity, freshness and days since activity.
cwdpathitemstargetcontent
io.github.mrfentmen由 GitHub 帳號 mrfentmen 發布v1.0.0更新於 Nov 21, 2026
Real local JSON analysis of portfolio link audit in the Resumes lane. 25 MCP tools, no paywall.
發布方自己的服務:audit.domains - Domain Valuation
本機 MCP 伺服器,以 JSON 稽核作品集連結稽核項目集合:涵蓋率、缺口、風險、就緒評分與後續步驟。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
參照 儲存庫 中的啟動說明。
One repo for three families of servers, each subtree keeping its own layout and tooling so it can still be built, run and published on its own.
Most servers read public data with no key of their own; the ones wrapping a vendor API take
that vendor's key. Nothing in this repo asks a caller to pay. On 2026-10-17 the
licence machinery was removed for good: the per-tool src/license.ts gates are gone from the
MCP servers, and the A2A and ACP trees no longer carry the hosted licence-gateway half — the
skills that used it now answer with an explicit not-implemented stub. Nothing here asks a
caller to pay, and nothing they run is refused with a buy link.
Nothing here is generated: each subtree's README says what its servers read, and every server
has its own unit tests (mcp/servers/<slug>/tests, acp/agents/<name>/tests,
a2a/servers/<name>/tests) plus a live smoke check (tools/smoke*.py,
a2a/tools/smoke_all.py).
Nearly all of this is first-of-its-kind work, not a port of an existing catalogue. Before each
server or agent was built, it was checked against the official tool lists (the MCP registries,
agentclientprotocol.com's agent list and registry) and a live GitHub search for the same
domain, and the research logs record what was found and why it still counted as missing — see
mcp/MISSING.md, acp/MISSING.md and
a2a/docs/. Highlights:
published/; mcp/MISSING.md
documents the check that preceded every build: what was searched, what was skipped and why
the domain still counted as uncovered.session/request_permission for dataset reads, fs/write_text_file for a briefing file,
session/cancel for a conditional watch, image content blocks, a live SSE push feed), each
proved-unused in the wild by search at build time. Two more firsts carry their own proof:
the orchestrator is an agent whose feeds are agents — it
spawns sibling repo agents as real ACP child processes and merges their answers — and the
nyc pack is the first multi-agency city surface.acp/MISSING.md doubles as the public-feed atlas: every keyless
feed probed live, with its date, what it answered and whether it still works. The
published site renders that table at https://mrfentmen.github.io/awesome-servers/atlas.html.mcp/servers/<slug> (its own package.json, version and README).Creatures that use this corpus as their world live in the sibling repo
mrfentmen/superagents (public, with its own
claim-check in MISSING.md):
watchd/ obeys unchanged, plus the activation lines. Checks it can author today:
air thresholds, quake magnitudes within a radius, river gauges at flood stage.mrfentmen/fedora-hat: says "never miss" and
means it — one sentence installs the full crown of watches (air + quakes, gauge-named
flood) in one permissioned write, and your other questions are forwarded to the siblings
above with every row cited.mrfentmen/instink: compiles a skill into a
reflex — a matcher plus the answer it fires, with hit/miss counters and honest
promotion/demotion. The skill doc stays one step away, never deleted.mrfentmen/contextink: you say "do this" and
it acquires the context from the repo, git, and recent files so you don't have to explain
it; asks only the minimal high-information-gain questions when acquisition fails.mrfentmen/rewind: replays agent runs and mutates
one variable to see what would have happened. Replay + mutate + diff for agent traces.mrfentmen/scopink: checks if an action is within
the scope of what was asked. Detects scope creep in agent plans.mrfentmen/curious: proactively seeks information
it doesn't have. Scans for knowledge gaps, seeks answers, learns facts.mrfentmen/bored: uses idle time productively.
Consolidates memories, explores areas, prepares for tasks.Point the polymath at a checkout of this repo with AWESOME_SERVERS_HOME=$PWD/awesome-servers
and it federates across the two repos live.
published/)published/ holds one directory per npm package, byte-for-byte what the registry
serves: 1039 packages, every version matching npm latest.
published/INDEX.md is generated from the tree by python3 scripts/index-published.py.scripts/sync-published-snapshot.py re-downloads every package from npm; run it only
when every local fix has been published, because it overwrites dist/ from the tarballs.MCP_LICENSE_KEY): @mrfentmen/vg-resource-mcp.
Another 495 still ship tools that answer Not yet implemented; published/INDEX.md lists
every one of them.mrfentmen/awesome-servers) as its source.servers/ holds the older per-server source that predates the snapshot. Where the two
disagree, published/ is what users actually install.
來源:README.md,提交 cc63360
Count the portfolio link audit item collection by category. Returns spend, quantity, freshness and days since activity.
cwdpathitemstargetcontentScore portfolio link audit item readiness from 0 to 100 for coverage, condition, data quality, freshness and days since activity.
cwdpathitemstargetcontentShow category coverage for the portfolio link audit item collection as 0-1 ratios, plus unknown categories.
cwdpathitemstargetcontentList missing categories, expired items, expiring items and dependency gaps for the portfolio link audit item collection.
cwdpathitemstargetcontentRank risks: low coverage, expired stock, budget overruns, duplicates, worn items and missing data.
cwdpathitemstargetcontentCheck the portfolio link audit item collection against item cap, budget, coverage, expiry and metric targets.
cwdpathitemstargetcontentCompare category counts with the configured baseline and show surplus or shortfall.
cwdpathitemstargetcontentCalculate days since activity for every portfolio link audit item, with mean and target pass count.
cwdpathitemstargetcontentFind low-effort fixes: small category gaps, missing data, expired items and duplicates.
cwdpathitemstargetcontentMap collection dependencies: which configured groups are present, how many items cover them and what is missing.
cwdpathitemstargetcontentTest edge cases: empty collection, one item, duplicate ids, zero cost, expired items, missing dates and unknown categories.
cwdpathitemstargetcontentSummarize the portfolio link audit item audit: counts, top gaps, top risks and data issues.
cwdpathitemstargetcontentRank fixes by impact divided by effort. Returns a shortlist and the next five actions.
cwdpathitemstargetcontentValidate arbitrary portfolio link audit item JSON, report schema errors and warnings, and count valid items.
cwdpathitemscontentGroup portfolio link audit item items with the same category and normalized name. Shows ids and extra copies.
cwdpathitemstargetcontentMeasure days since activity spread, category-count variance and tag diversity.
cwdpathitemstargetcontentBenchmark lean, balanced and full collection sizes, plus readiness, coverage, metric and data targets.
cwdpathitemstargetcontentExplain the real tradeoffs: size vs coverage, cost vs use, freshness vs stock and data quality vs speed.
cwdpathitemstargetcontentDraft a practical checklist from gaps, high risks, missing data and budget.
cwdpathitemstargetcontentExport the full portfolio link audit item audit: target, metrics, gaps, risks, constraints, duplicates, benchmark and next steps.
cwdpathitemstargetcontentCompare two portfolio link audit item snapshots by item id and return added, removed and changed items.
after必填before必填Review dated portfolio link audit item snapshots and return readiness, cost and metric trends from first to last.
targethistory必填Score how much the audit can be trusted from data completeness, item count, cost coverage and quantity coverage.
cwdpathitemstargetcontentRecommend the next five actions from the ranked fix list, with quick wins alongside.
cwdpathitemstargetcontentList open questions that block a better audit: budget, data, expiry, duplicates and unknown categories.
cwdpathitemstargetcontent已滿足適用檢查項的 80%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
請在儲存庫或註冊中心條目中宣告授權條款。
domains.audit官方發布者
確定性的網域名稱估值服務:提供公允價值區間、真實可比成交紀錄、可用性查詢,以及經 DNS 驗證的待售網域市場。
news.prh官方發布者
一個遠端 MCP 端點,用於稽核 OpenAPI 規格並偵測 API 變更,每次分析透過 Base 上的 x402 收取 0.10 USDC。

由 GitHub 帳號 zColdWater 發布
Audit brand domains, USPTO trademarks, SPF/DKIM/DMARC email, and AI search (llms.txt) readiness.

由 GitHub 帳號 Berrkaydev 發布
由 Apify 託管的 MCP 伺服器,讓助理對網站執行技術性 SEO 稽核:失效連結、重新導向、頁面問題、網站地圖和 AI 爬蟲存取權限。
由 GitHub 帳號 kwizzlesurp10-ctrl 發布
遠端 MCP 伺服器,用來稽核線上網站的 AI 爬蟲存取、GEO/AEO 就緒度與 JSON-LD 引用結構,付費稽核按次以 USDC 結算。