mcp-registry/io.github.tang-vu/keryx · v0.3.18
Also listed as glama/tang-vu/keryx
As of 2026-10-23 02:44 UTC, the Tang Vu Keryx MCP server is degraded with a Glimind reliability score of 58/100 (grade D). Over the last 30 days it answered 92.5% of Glimind's liveness checks. It had 115 outages in 90 days, with a median recovery of 12 minutes.
Autonomous research agent that pays every source it cites in USDC on Arc via x402 micropayments.
Claude Code
claude mcp add --transport http tang-vu-keryx-mcp-server https://keryx.cc/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"tang-vu-keryx-mcp-server": {
"type": "http",
"url": "https://keryx.cc/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
Reachable 92.5% of the time over the last 30 days; median recovery 12 min.
Agents fail over to an alternative the first time a call fails. Add health checks and restart-on-failure, and avoid cold starts on serverless hosts.
33 parameter(s) across 12 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
4 tool(s) have parameters with no type (no type/enum/anyOf/$ref).
Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →
Handshake + tools/list takes ~2,125 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
6 tools share an identical description with another tool on this server.
Make each description say how the tool differs from its siblings, or the model will pick between them at random. How to fix →
In the last 30 days: 0 tool(s) removed and 8 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 12 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.tang-vu%2Fkeryx/fixes
{
"name": "draft_check",
"description": "Split a private passage into sentences, bind citation markers ([3], cite{key}, [@key], Author (Year)) to a BibTeX, RIS or DOI/link reference list, and compare each cited sentence with source text you supply. Each verdict (supported, partly-supported, not-found, source-unavailable) carries a verbatim excerpt of that text or states that no supporting passage was found; a source without supplied text is always source-unavailable. Deterministic wording comparison, not semantic review. No fetching, m",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"check": {
"description": "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 written citations. No fetching or payment. See docs/draft-check.md.",
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
},
"title": "Check a draft's cited claims against supplied source text"
}{
"name": "evidence_draft",
"description": "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 aut",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"draft": {
"description": "Version-1 private-evidence-draft contract, at most 65536 UTF-8 bytes. Optional assembly {mode:append} or {mode:regenerate,themeId} quotes retained text without model calls; optional readingStatuses separates caller-observed unread/unavailable records from unknown status. See docs/evidence-drafts.md and docs/engineering/related-work283-completion-2026-10-12.md.",
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
},
"title": "Assemble a private retained-evidence draft"
}{
"name": "evidence_procurement",
"description": "Assess missing evidence requirements, supplied provider offers, selections, deliveries and caller reviews with the shared private evidence procurement contract. Amounts are exact integer micro-USDC. Signature and content-binding checks do not establish delivery quality, buyer authority, payment or settlement. No fetching, model, provider, database, history, purchase, escrow or reward I/O. Caller selections and reviews are assertions, not financial authorization. Inputs and results may be retaine",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"format": {
"description": "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.",
"type": "string"
},
"packet": {
"description": "Version-1 private-evidence-procurement packet, at most 65536 UTF-8 bytes. Supply original inputs, never a derived procurement result.",
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
},
"title": "Plan and inspect private evidence procurement"
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.tang-vu/keryx"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.tang-vu/keryx"}) over MCP.
research ~497 tokensdeliverable_acceptance_submit ~364 tokenshistory_private_jobs_export ~341 tokenspaper_lookup ~334 tokenshistory_private_jobs_list ~308 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fio.github.tang-vu%2Fkeryx?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.tang-vu%2Fkeryx?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.tang-vu%2Fkeryx.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.tang-vu%2Fkeryx.svg :target: https://glimind.com/server/mcp-registry%2Fio.github.tang-vu%2Fkeryx?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:97c0cfc023656324…, first seen 2026-10-21, included at leaf 39515 of 49,552. Version history · verify what your client received.
Compare: most reliable knowledge servers · most reliable files servers · most reliable communication servers · most reliable productivity servers · most reliable data servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-23 02:44 UTC, the Tang Vu Keryx MCP server is degraded with a Glimind reliability score of 58/100 (grade D). Over the last 30 days it answered 92.5% of Glimind's liveness checks. It had 115 outages in 90 days, with a median recovery of 12 minutes.
Tang Vu Keryx MCP server advertises 27 tools, including ask_keryx, deliverable_acceptance_read, deliverable_acceptance_submit, draft_check, evidence_draft.
Point your MCP client at this streamable-http endpoint: https://keryx.cc/mcp
Glimind scanned all 25 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.