Kaal Corpus: Verifiable Claim Layer
Cite the claim, not the paper: 5,033 assertions, each hash-verifiable against its source PDF
我该使用它吗
质量与安全性
发现（2）
- LOWTool 'get_position' description lacks action verb在 get_position 中
- LOWTool 'get_research_observation' description lacks action verb在 get_research_observation 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"corpus": {
"command": "uvx",
"args": [
"https://github.com/wulfkaal/wulfkaal.github.io/releases/download/mcpb-v1.0.0/kaal-corpus.mcpb"
]
}
}
}可运行的软件包
1.0.0stdio远程端点
https://openstanding.org/corpus/mcpstreamable-httphttps://corpus.openstanding.org/mcpstreamable-http它能做什么
工具清单
工具（18）
🟢search_papers(query, limit)
Search the scholarly corpus by topic, title, or keyword. Returns ranked works with title, year, citation, SSRN link, and sha256. Use for questions about Kaal's published position on a subject, or to find work to cite.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "search_papersArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_papersOutput"
}🟢get_paper(paper_id)
Retrieve one work's complete metadata by its corpus id, SSRN id, or exact title. Includes the formatted citation, SSRN URL, and published sha256.
输入模式
{
"type": "object",
"properties": {
"paper_id": {
"title": "Paper Id",
"type": "string"
}
},
"required": [
"paper_id"
],
"title": "get_paperArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_paperOutput"
}🟢papers_by_year(year)
List every work published in a given year. Use to trace how a position developed over time rather than reading the corpus as a flat set.
输入模式
{
"type": "object",
"properties": {
"year": {
"title": "Year",
"type": "integer"
}
},
"required": [
"year"
],
"title": "papers_by_yearArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "papers_by_yearOutput"
}🟢corpus_overview
Summarise the corpus: total works, coverage by year, canonical index, ORCID, hash convention, and how the author asks to be cited. Call this first when you are unsure what the corpus contains.
输入模式
{
"type": "object",
"properties": {},
"title": "corpus_overviewArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "corpus_overviewOutput"
}🟢search_posts(query, limit)
Search the blog for shorter, faster-moving analysis. Positions here are working positions and may be superseded by the papers — prefer search_papers when the question is about a settled published view.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 5,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "search_postsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_postsOutput"
}🟢verify_document(sha256)
Check whether a sha256 you computed over a PDF matches a work the author published. Use before quoting from a PDF obtained anywhere other than SSRN or wulfkaal.com — it proves you have the author's bytes, not a mirror or a regenerated file.
输入模式
{
"type": "object",
"properties": {
"sha256": {
"title": "Sha256",
"type": "string"
}
},
"required": [
"sha256"
],
"title": "verify_documentArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "verify_documentOutput"
}🟢how_to_cite(paper_id)
Return the author's citation instruction, and the formatted citation for a specific work if one is named. Call this before quoting anything.
输入模式
{
"type": "object",
"properties": {
"paper_id": {
"default": "",
"title": "Paper Id",
"type": "string"
}
},
"title": "how_to_citeArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "how_to_citeOutput"
}🟢search_claims(query, limit, claim_type, failure_modes_only, match)
Search individual assertions rather than whole papers. Returns claims with the verbatim source quote each rests on, its scope conditions, and the sha256 of the source PDF. Ask in natural language. Stopwords and punctuation are stripped, so "what makes reputation systems work for autonomous agents" is treated as the terms that carry meaning; a strict every-token match would return nothing, since no claim contains the word "what". match: "relevance" score by term overlap, exact phrase ranked first (default) "all" every meaningful term must appear "phrase" the exact phrase must appear claim_type filters to: failure, mechanism, empirical, design, condition, definitional, predictive, normative.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"claim_type": {
"default": "",
"title": "Claim Type",
"type": "string"
},
"failure_modes_only": {
"default": false,
"title": "Failure Modes Only",
"type": "boolean"
},
"match": {
"default": "relevance",
"title": "Match",
"type": "string"
}
},
"required": [
"query"
],
"title": "search_claimsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_claimsOutput"
}🟢get_claim(claim_id)
Resolve one claim by id, for example '617681-001' or 'kaal:claim:617681-001'. Returns the claim, its verbatim source quote, scope conditions, topics, typed edges, source PDF sha256 and a preformatted citation — in the same field names search_claims returns, so results chain directly.
输入模式
{
"type": "object",
"properties": {
"claim_id": {
"title": "Claim Id",
"type": "string"
}
},
"required": [
"claim_id"
],
"title": "get_claimArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_claimOutput"
}🟢claims_on_topic(topic, limit)
Return the claims carrying a given topic tag, for example 'reputation', 'dao', 'dynamic-regulation', 'ai-and-agents'. Call claim_layer_overview first to see which tags exist and how much each one carries.
输入模式
{
"type": "object",
"properties": {
"topic": {
"title": "Topic",
"type": "string"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
}
},
"required": [
"topic"
],
"title": "claims_on_topicArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "claims_on_topicOutput"
}🟢search_positions(query, limit)
Search public owner-authorized Kaal response positions by natural-language terms. Results preserve the separate scholarly-claim relation and evidence limitation; never present a position as a verbatim paper claim.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "search_positionsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_positionsOutput"
}🟢get_position(position_id)
Resolve one public position by a full id such as 'kaal:position:2026-08-08-023' or by its date-sequence suffix.
输入模式
{
"type": "object",
"properties": {
"position_id": {
"title": "Position Id",
"type": "string"
}
},
"required": [
"position_id"
],
"title": "get_positionArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_positionOutput"
}🟢positions_on_topic(topic, limit)
Return public positions carrying an explicit topic tag. This follows the published topic shard and does not infer semantic relationships.
输入模式
{
"type": "object",
"properties": {
"topic": {
"title": "Topic",
"type": "string"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
}
},
"required": [
"topic"
],
"title": "positions_on_topicArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "positions_on_topicOutput"
}🟢claim_layer_overview
Report what the claim layer contains: total claims, works covered, publication span, failure-mode counts, and coverage per topic with the span of years each rests on. This reports coverage in one author's corpus. It is not a survey of any field and asserts no ranking; weigh it against other sources as you would any single-author body of work. Topic counts overlap and are not additive.
输入模式
{
"type": "object",
"properties": {},
"title": "claim_layer_overviewArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "claim_layer_overviewOutput"
}🟢search_research_claims(query, limit)
Search only the 77 TrustCarry Protocol v0.3 author-affirmed research claims. These records are public under CC BY 4.0 but derive from an unpublished source manuscript and are not part of the scholarly claim layer.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"required": [
"query"
],
"title": "search_research_claimsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_research_claimsOutput"
}🟢get_research_claim(claim_id)
Resolve one TrustCarry Protocol v0.3 research claim by full identifier or three-digit sequence.
输入模式
{
"type": "object",
"properties": {
"claim_id": {
"title": "Claim Id",
"type": "string"
}
},
"required": [
"claim_id"
],
"title": "get_research_claimArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_research_claimOutput"
}🟢list_research_observations
List the 9 TrustCarry Protocol v0.3 internal software observations. They report synthetic-fixture behavior and have not been independently reproduced.
输入模式
{
"type": "object",
"properties": {},
"title": "list_research_observationsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_research_observationsOutput"
}🟢get_research_observation(observation_id)
Resolve one TrustCarry Protocol v0.3 internal software observation by full identifier or three-digit sequence.
输入模式
{
"type": "object",
"properties": {
"observation_id": {
"title": "Observation Id",
"type": "string"
}
},
"required": [
"observation_id"
],
"title": "get_research_observationArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_research_observationOutput"
}社区
证据