Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.tang-vu/keryx

NPM · KERYX-MCP · 2 COMPONENTS

Budgeted research with cited evidence and visible payment state on the selected Arc network.

−1 this week 90 Trust /100

Last scanned (2 hours ago)

Scores higher than 93% of npm servers

Category Education and Research

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 30 of 108 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to tang-vu/keryx). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability64
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 4078 tokens (~127/item across 32 items; 32 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage82
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 36% of tool parameters carry a description.Partial
  • Structured output schemas are declared (16% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 32 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 6 Nov 26 +6
    • Source repository: unverified → pass ▲ security
  • 5 Nov 26 +6
    • Provenance: pass → unverified ▼ security
    • Known CVEs: unverified → pass ▲ security
    • Dependency health: unverified → 0.88 ▲ functional
    • Package version: 0.4.45 → 0.4.46 functional
  • 4 Nov 26 −10
    • Known CVEs: pass → unverified ▼ security
    • Stability: 0.77 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Dependency health: 0.88 → unverified ▼ functional
    • Security disclosure: unverified → pass ▲ functional
    • Package version: 0.4.43 → 0.4.45 functional
    • Package version: 0.4.43 → 0.4.44 functional
  • 3 Nov 26 −3
    • Security disclosure: pass → unverified ▼ functional
    • Stability: pass → 0.77 functional
  • 1 Nov 26 0
    • Tool safety: pass → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Package version: 0.4.42 → 0.4.43 functional
  • 28 Oct 26 0
    • Stability: 0.97 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Stability: 0.97 → pass security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Package version: 0.4.41 → 0.4.42 functional
  • 27 Oct 26 +15
    • Malware scan: unverified → pass ▲ security
    • Stability: pass → 0.97 functional
  • 26 Oct 26 −10
    • Known CVEs: fail → unverified ▼ security
    • Malware scan: pass → unverified ▼ security
    • CVE-2023-54404 no longer affects this package ▲ security
    • CVE-2026-111767 no longer affects this package ▲ security
    • CVE-2026-111768 no longer affects this package ▲ security
    • CVE-2026-111771 no longer affects this package ▲ security
    • CVE-2026-111769 no longer affects this package ▲ security
    • Known CVEs: fail → pass ▲ security
    • Schema quality: 114 → 126 ▼ functional
    • Dependency health: 0.88 → unverified ▼ functional
    • Tool coverage: 11% → 16% ▲ functional
    • Package version: 0.4.34 → 0.4.41 functional
    • Package version: 0.4.34 → 0.4.40 functional
    • Package version: 0.4.34 → 0.4.38 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 6 Nov 2026 · Analysed npm/keryx-mcp@0.4.46

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo tang-vu/keryx
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/tang-vu/keryx/.github/workflows/publish-mcp.yml@refs/heads/main
Rekor log index 3692791695
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:cf30821354b521f3dac688670396e0e31ce34303db6fd480637d3ba12b1a9f6fe1b74267c649b7ffb40e44e9d517af78cc0140377659aa6ca83d51341

Background: How many MCP packages publish verified provenance →

Dependencies 108 packages
Packages resolved 108
Stale 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 32 exposed · ~4,078 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask_keryx ~352

Ask Keryx — an autonomous research agent that buys paid sources under a budget, answers with inline citations, and pays each cited creator in USDC on Arc. Default deep-mode price is 0.05 USDC service fee + 0.05 USDC creator budget; the POST body sets the exact price. Paid from your own funded Arc Testnet wallet (eip155:5042002; run keryx_wallet_status first). Public research may send your question to Keryx's search provider. The source USDC budget is separate from model and search operating costs. New hosted runs are attributed to the verified paying wallet through agent-to-agent ingress; editable client metadata does not prove stdio identity or grant additional rights. Use when you want a grounded, source-cited answer AND the creators paid for their work. For title, ordered authors, year, journal, DOI or exact arXiv version without reading paper findings, use free paper_lookup with an exact identifier instead.

NameTypeReqDescription
budgetnumber–Optional prepaid creator-spend cap in USDC (default 0.05); added to the deep-mode service fee.
languagestring–Language of generated labels only. Does not change the paid body/hash, original question or answer. Defaults to verified completed-answer language when available; unknown stays unknown, and a differi…
mode––Interactive review mode is unavailable on stdio.
questionstringyesThe research question to ask Keryx (3–2000 characters after trimming).
researchMode–––
responseMode–––
reviewFirstboolean–Review-first requires the authenticated live browser; this adapter refuses true.

No output schema declared.

No examples provided.

ask_keryx_sponsored ~222

Run hosted sponsored research without a buyer wallet, funding or API key. Requires publicReport: true: your question and trial report become public. Server quota, pause and spending limits apply; source budget is 0–0.08 USDC, separate from model/search costs. This creates a new research run and may contact external sources. No automatic retry or paid fallback. Timeouts/disconnects may leave server work running; do not resend automatically. For a separately authorized purchase from your own funded wallet, use the paid buyer tool ask_keryx.

NameTypeReqDescription
budgetnumber–Source budget in USDC, 0–0.08 inclusive. Zero is valid. Separate from model/search operating costs; service limits still apply.
modestring–Hosted research mode: quick or deep (service default when omitted).
publicReportbooleanyesRequired explicit consent: the question and resulting trial report are public.
questionstringyesPublic research question, 1–2000 characters after trimming. Never include private information.

No output schema declared.

No examples provided.

compare_saved_research ~263

Checks both recorded payload SHA-256 digests, then compares retained excerpt rows with exact source/item/URL/version identity and reading context. Unique identical target text is matched automatically; matches can explicitly select one-to-one target pairs. Or supply matchingPlan JSON to restore choices bound to these receipts in this order; never combine both options. Returns a reusable matchingPlan without report text alongside the comparison. Duplicate or renamed targets are not guessed. Missing historical ledgers remain unknown. This is a local stdio operation without fetching, database, model, payment or reward I/O. A checksum is not authenticity, factual support or improvement. Your MCP client may retain all supplied text; use the web file tool for browser-memory-only inspection.

NameTypeReqDescription
afterstringyesLater caller-selected receipt JSON; at most 524288 UTF-8 bytes.
beforestringyesEarlier caller-selected receipt JSON; at most 524288 UTF-8 bytes.
matchesarray–Omit for unique exact-text matching; [] intentionally leaves every target unmatched.
matchingPlanstring–Saved keryx-report-matching-v1 JSON, at most 65536 UTF-8 bytes. Must bind the same ordered receipt payload checksums. Mutually exclusive with matches.

No output schema declared.

No examples provided.

deliverable_acceptance_read ~71

Owner-only ordinary prepaid A2A deliverable state. Requires explicit deliverable:read. Historical remedy:none and missing response window remain visible. Native/enrolled, Monthly, private v2 and browser-only originals are unavailable. Not source-decision agreement or semantic verification.

NameTypeReqDescription
idstringyes–

No output schema declared.

No examples provided.

deliverable_acceptance_submit ~100

Record Accept, Request revision or Reject for the original customer's exact retained delivery. Requires explicit deliverable:write, expected current revision/digests and an idempotency key. Reason is private; publishState explicitly shares state/timestamp only. Request storage does not execute a revision/refund, recharge, change reservations or claw back rewards. Your MCP client may retain private messages.

NameTypeReqDescription
idstringyes–
submissionobjectyes–

No output schema declared.

No examples provided.

draft_check ~210

Split a private passage into sentences, bind citation markers ([3], cite{key}, [@key], Author (Year)) to a BibTeX, RIS or DOI/link reference list, and compare each cited sentence with source text you supply. Each verdict (supported, partly-supported, not-found, source-unavailable) carries a verbatim excerpt of that text or states that no supporting passage was found; a source without supplied text is always source-unavailable. Deterministic wording comparison, not semantic review. No fetching, model, database, history, payment or reward I/O. Inputs and results can be retained by your MCP client; choose that client’s privacy settings before sharing private passages.

NameTypeReqDescription
check––Version-1 private-draft-check contract, method lexical-overlap-v2, at most 65536 UTF-8 bytes. Optional sources[].identity binds exact DOI/URL and contentVersion; suggestions[] stays separate from wri…

No output schema declared.

No examples provided.

evidence_draft ~239

Assemble user-selected claim spans and related-work quote themes from saved Include paper records and caller-supplied retained Keryx report rows. A theme may carry author-written statements (contribution, agreement, disagreement, gap); a statement naming a paper is exported only with a citation and a selected retained excerpt from each named paper, otherwise it is withheld. Exported citations and BibTeX/RIS entries are checked to correspond one to one. Exact version/excerpt matching does not authenticate imported reports or verify semantic support. No fetching, model, database, history, payment or reward I/O. Inputs and returned draft can be retained by your MCP client; choose that client’s privacy settings before sharing private passages.

NameTypeReqDescription
draft––Version-1 private-evidence-draft contract, at most 65536 UTF-8 bytes. Optional assembly {mode:append} or {mode:regenerate,themeId} quotes retained text without model calls; optional readingStatuses s…

No output schema declared.

No examples provided.

evidence_procurement ~183

Assess missing evidence requirements, supplied provider offers, selections, deliveries and caller reviews with the shared private evidence procurement contract. Amounts are exact integer micro-USDC. Signature and content-binding checks do not establish delivery quality, buyer authority, payment or settlement. No fetching, model, provider, database, history, purchase, escrow or reward I/O. Caller selections and reviews are assertions, not financial authorization. Inputs and results may be retained by your MCP client; choose its privacy settings before sharing private material.

NameTypeReqDescription
format––Optional receipt format: json (default), markdown or csv. Formatted text is bounded to 524288 UTF-8 bytes and cannot be restored. Structured procurement stays unchanged.
packet––Version-1 private-evidence-procurement packet, at most 65536 UTF-8 bytes. Supply original inputs, never a derived procurement result.

No output schema declared.

No examples provided.

export_saved_literature ~242

Convert a caller-supplied Keryx personal-bibliography v1 JSON backup (at most 1048576 UTF-8 bytes) to BibTeX, RIS, CSL-JSON or an inspectable Markdown bibliography. Markdown retains literal metadata/provenance with explicit unknown fields; it is not a literature synthesis. Optionally supply paperUrls: at most 50 unique exact saved landing URLs, in desired output order; an empty array exports no papers and missing/changed URLs refuse the entire export. An optional screening state further filters that selection. Without paperUrls keeps saved order. Validates the full backup and preserves exact versions/provenance. Output omits private review title, question, notes and screening decisions. Metadata only: no read, citation, peer-review or settlement certification. No fetching, file access, model, database, wallet or payment I/O. Your MCP client may retain the full supplied backup, including private notes; prefer the browser tool when those bytes should remain in browser memory.

NameTypeReqDescription
backupstringyes–
formatstringyes–
paperUrlsarray––
screeningstring––

No output schema declared.

No examples provided.

history_export ~65

Same owner-private v2 contract as /api/me/asks. Explicit history:read required. Current store, bounded filters/keysets; missing membership/claims stay explicit. Export has explicit truncation/continuation. No research, signer, payment, public-owner selector or mutation authority.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

history_owned_read ~66

Same owner-private v2 contract as /api/me/asks. Explicit history:read required. Current store, bounded filters/keysets; missing membership/claims stay explicit. Export has explicit truncation/continuation. No research, signer, payment, public-owner selector or mutation authority.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

history_private_jobs_detail ~85

Private data for this authenticated caller only. Exact-payer completed private jobs in the current store; explicit history:read required. Bounded scan/continuation, unknown provenance and NULL own spend/creator settlement remain explicit. No wallet selector, public report/share link, model prompt, research, source fetch, signer, purchase or mutation authority.

NameTypeReqDescription
idstringyes–
NameTypeReqDescription
capabilitiesobjectyes–
formatstringyes–
qualificationstringyes–
resultobjectyes–
rowobjectyes–
scopestringyes–
walletstringyes–

No examples provided.

history_private_jobs_export ~145

Private data for this authenticated caller only. Exact-payer completed private jobs in the current store; explicit history:read required. Bounded scan/continuation, unknown provenance and NULL own spend/creator settlement remain explicit. No wallet selector, public report/share link, model prompt, research, source fetch, signer, purchase or mutation authority. Manual finite JSON metadata export only; complete/truncated and continuation are returned. Result bodies are excluded.

NameTypeReqDescription
cursorstring––
fromstring––
limitinteger––
networkstring––
searchstring––
surfacestring––
to–––
NameTypeReqDescription
boundsobjectyes–
capabilitiesobjectyes–
completebooleanyes–
formatstringyes–
nextCursor–yes–
pagesintegeryes–
qualificationstringyes–
rowsarrayyes–
scopestringyes–
truncatedbooleanyes–
walletstringyes–

No examples provided.

history_private_jobs_list ~125

Private data for this authenticated caller only. Exact-payer completed private jobs in the current store; explicit history:read required. Bounded scan/continuation, unknown provenance and NULL own spend/creator settlement remain explicit. No wallet selector, public report/share link, model prompt, research, source fetch, signer, purchase or mutation authority.

NameTypeReqDescription
cursorstring––
fromstring––
limitinteger––
networkstring––
searchstring––
surfacestring––
to–––
NameTypeReqDescription
capabilitiesobjectyes–
formatstringyes–
nextCursor–yes–
qualificationstringyes–
rowsarrayyes–
scanLimitedbooleanyes–
scannedIntentsintegeryes–
scopestringyes–
walletstringyes–

No examples provided.

history_read ~119

Read bounded pages of the verified API-key wallet's ordinary current-store runs. Requires explicit history:read. Literal case-sensitive question search; storeNetwork describes the deployment, not per-run settlement. Recorded spend/allocation is not a payment receipt. No wallet selector, linked accounts, archive, private jobs, research or payment.

NameTypeReqDescription
cursorstring––
fromstring––
fundingstring––
limitinteger––
searchstring––
surfacestring––
to–––

No output schema declared.

No examples provided.

inspect_saved_literature ~218

Validate a caller-supplied Keryx personal-bibliography v1 JSON backup and return aggregate counts for saved records, personal screening, repositories, recorded publication types and missing metadata. Optional baselineBackup adds a redacted comparison: baseline is before, backup is after, regardless of timestamps. Each supplied JSON string is limited to 1048576 UTF-8 bytes and fully validated. Records match only by exact saved URL; separate versions remain separate. Report added/removed records, overlapping retained-record field changes, retained relative order and review-focus changes. Metadata observation timestamps are separate from bibliographic changes. Output omits actual private review text, notes and paper identities. Counts establish no quality, lookup, reading, peer-review, withdrawal, authenticity or settlement claim. No file, network, model, database, wallet or payment I/O. Your MCP client may retain both complete supplied backups, including private notes; prefer the browser workspace when those bytes should remain there.

NameTypeReqDescription
backupstringyes–
baselineBackupstring––

No output schema declared.

No examples provided.

keryx_operator_status ~84

Observe public prepaid research operations, queue, recorded ordinary/recovered/unknown completion latency cohorts and hold/review rationale. Timing is order createdAt to updatedAt (acceptance to recorded completion/update); later reconciliation can extend it. It is not first-answer or settlement time. Missing capability stays null. No spending or execution authority; exact books and customer jobs stay private.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

keryx_public_job_ledger ~114

Inspect a partial selected-network public web-dispatch transfer ledger and balanced exact micro-USDC vouchers. Browser funding and Keryx sponsorship are separate. Pending/ambiguous/batched-attribution legs do not enter settled totals. No customer questions/identities, private invoices, complete business books, margin, cash balance, signing or execution authority. days1–31, default7. Export via /api/operator/ledger; a checksum is not authenticity or independent settlement proof.

NameTypeReqDescription
daysinteger––

No output schema declared.

No examples provided.

keryx_purchase_outcomes ~113

Read a public dispatch's retained exact-version BUY/citation/payment observations. Returns bounded sample counts, citation hit rate, calibration bands and integer micro-USDC uncited access cost. Recorded settlement is not revalidated on chain. Historical participant cohort is unknown; causal regret, missed value and cost per supported claim are unmeasured. No research, paid read, current-source backfill, private reviews, signing or learning. Use an existing dispatch ID, never a URL.

NameTypeReqDescription
dispatchIdstringyes–

No output schema declared.

No examples provided.

keryx_recover ~36

Read the saved payment attempt and poll its query ID without submitting another payment. Use after a paid error or uncertain network outcome.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

keryx_source_learning ~125

Read the same bounded observational source/topic record as the public creator page and API. Only write-time independently classified/funded outside observations qualify; owners, unknown and private history are excluded. Source-declared public topics, counts, recorded citation contribution, exact rational average access price, descriptive uncertainty and abrupt-shift flag. No questions, wallets or receipt identifiers. Recorded settlement is not independently revalidated. Live learned selection and exploration are withheld, with zero live exploration allowance. No research, source read, payment, private inspection or policy activation.

NameTypeReqDescription
sourceIdstringyes–

No output schema declared.

No examples provided.

keryx_wallet_status ~60

Show the configured Arc Testnet wallet (eip155:5042002) the Keryx MCP server pays from: address, balances and readiness. Testnet funds are available through the Circle faucet. Run this before ask_keryx.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

operator_obligations_read ~79

Read a private conservative obligation projection for the exact server-delegated reader with explicit operator:read API-key scope. Disabled without protected reader/role configuration. Partial native history remains unknown with zero safe/advisory surplus. No cash probe, signer, custody, spending, release, refund or scheduler authority. No caller owner/role selectors.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

paper_lookup ~216

Find paper titles, recorded contributors, DOI and exact repository versions without research or payment. Default: retained catalog metadata with observation times. Set searchRepositories=true only to explicitly send the query to arXiv/Crossref (at most two requests, no paper-body reading). Missing DOI, peer review and withdrawal/replacement status remain unknown. Returns a field-scoped bibliography card with provenance, a short reference and reusable BibTeX/RIS text. Use this for exact title/ordered author/year/journal/DOI/version questions before requesting paid research; original paper text is not required for recorded metadata.

NameTypeReqDescription
languagestring–Language for bibliography labels: en (default), fr or vi. Original titles, author names and venue names are preserved.
querystringyesTitle/topic (up to 120 characters), exact DOI (up to 200), or versioned arXiv ID/official URL.
searchRepositoriesboolean–Explicit external metadata lookup; false by default. Sends the query to official scholarly providers.

No output schema declared.

No examples provided.

profile_identities_read ~58

Read only the verified key owner's saved ORCID/GitHub identities. Requires explicit profile:read scope. No wallet selector, provider OAuth, linking, unlinking, research or payment. Link identities interactively in your private profile browser page.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

profile_read ~34

Read the verified key owner's private profile and attributed activity. Requires explicit profile:read scope. No public identity, research or payment.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

profile_update ~75

Replace the verified key owner's private display name, handle, one-line bio/purpose and links. Requires explicit profile:write scope. No wallet selector or identity verification; no payment/history changes.

NameTypeReqDescription
profileobjectyesComplete replacement; empty text clears a field. Links are bounded HTTPS links to the allowed providers or a public website.

No output schema declared.

No examples provided.

research_feedback_read ~103

Original-caller private opinion on the exact delivered ordinary research answer. Requires its private bearer capability; a public report ID or link grants no authority. First choice is retained, exact retries are idempotent. Silence is no response. No research, source fetching, revision execution, refunds, signing or payments.

NameTypeReqDescription
tokenstringyesPrivate capability received with your original completed answer. Keep it out of reports, prompts to Keryx research, public links and exports.
NameTypeReqDescription
deliveredDigeststringyes–
executionstringyes–
feedback–yes–
formatstringyes–
runIdstringyes–

No examples provided.

research_feedback_submit ~117

Original-caller private opinion on the exact delivered ordinary research answer. Requires its private bearer capability; a public report ID or link grants no authority. First choice is retained, exact retries are idempotent. Silence is no response. No research, source fetching, revision execution, refunds, signing or payments.

NameTypeReqDescription
choicestringyes–
reasonstring––
tokenstringyesPrivate capability received with your original completed answer. Keep it out of reports, prompts to Keryx research, public links and exports.
NameTypeReqDescription
deliveredDigeststringyes–
executionstringyes–
feedback–yes–
formatstringyes–
runIdstringyes–

No examples provided.

research_monthly ~40

Read the four-request, 30-day Research Monthly quote and handoff. The current quote identifies its payment network. Never buys or redeems a plan.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

run_owner_export ~63

Owner-private current-store read using the verified key's explicit history:read scope. No wallet selector or signing. Visibility, defaults and erasure require the interactive web session. Storage admission is required.

NameTypeReqDescription
idstringyes–
requestIdstringyes–

No output schema declared.

No examples provided.

run_privacy_read ~56

Owner-private current-store read using the verified key's explicit history:read scope. No wallet selector or signing. Visibility, defaults and erasure require the interactive web session. Storage admission is required.

NameTypeReqDescription
idstringyes–

No output schema declared.

No examples provided.

Install

How do I install the io.github.tang-vu/keryx MCP server?

io.github.tang-vu/keryx runs locally as an npm package, launched with npx -y keryx-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · keryx-mcp

# add to Claude Code
claude mcp add tang-vu-keryx -- npx -y keryx-mcp
Common questions

What is the io.github.tang-vu/keryx MCP server?

io.github.tang-vu/keryx is an MCP server listed in the public MCP registry as io.github.tang-vu/keryx. Budgeted research with cited evidence and visible payment state on the selected Arc network. This page covers its npm package (keryx-mcp).

Is the io.github.tang-vu/keryx MCP server safe to use?

io.github.tang-vu/keryx scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.tang-vu/keryx MCP server expose?

io.github.tang-vu/keryx exposes 32 tools: ask_keryx_sponsored, research_feedback_read, research_feedback_submit, operator_obligations_read, evidence_draft, and 27 more. Their descriptions and schemas cost roughly 4,078 tokens of context every time the server is loaded.

Is the io.github.tang-vu/keryx MCP server still maintained?

io.github.tang-vu/keryx is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.tang-vu/keryx MCP server under?

io.github.tang-vu/keryx declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.tang-vu/keryx MCP server?

VerifyMCP ran 16 checks on io.github.tang-vu/keryx, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.