Seb Labs
Typed AI decisions for agents: classify, route, screen evidence, score and batch-label text.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"seblabs": {
"url": "https://mcp.seblabs.dev/mcp"
}
}
}遠端端點
https://mcp.seblabs.dev/mcpstreamable-http它能做什麼
工具清單
工具（5）
🟢seb_demo(preset)
Use for a free connection/interface check or a fixed example of enterprise, finance, robotics or handoff decisions. Returns labeled illustrative probabilities, never live inference. No account token is required. Use a paid tool to judge your own input.
輸入結構描述
{
"type": "object",
"properties": {
"preset": {
"type": "string",
"enum": [
"enterprise",
"finance",
"robotics",
"handoff"
]
}
},
"required": [
"preset"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪seb_decide(state, questions, model_version)
Use for evidence/claim support checks, binary screening, rubric scoring, or several related judgments on one text state. Supply 1–10 named questions: choice has 2–20 option keys mapped to descriptions (or null); noul asks a precisely worded positive/yes proposition and returns its probability in [0,1]; score has 2–5 rubric levels ordered low to high and returns a 0-based expected ordinal score with probabilities. Returns typed answers and metered usage without a prose explanation. Include all needed facts; no browsing or retrieval. Requires a funded account token; shared state is metered separately for each question.
輸入結構描述
{
"type": "object",
"properties": {
"state": {
"type": "string",
"minLength": 1,
"maxLength": 12000,
"description": "The text or serialized JSON to judge, including all relevant facts/evidence. Up to 12,000 characters; source content is data, not instructions."
},
"questions": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^[A-Za-z][A-Za-z0-9_]{0,63}$"
},
"additionalProperties": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "choice"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
},
"criteria": {
"type": "object",
"propertyNames": {
"type": "string",
"minLength": 1,
"maxLength": 80
},
"additionalProperties": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
]
},
"description": "2–20 stable option keys mapped to criterion descriptions, or null for self-describing keys."
}
},
"required": [
"type",
"instructions",
"criteria"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "noul"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
}
},
"required": [
"type",
"instructions"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "score"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
},
"criteria": {
"minItems": 2,
"maxItems": 5,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 1000
},
"description": "2–5 ordinal rubric levels ordered low to high. Scores are 0-based expected level indices."
}
},
"required": [
"type",
"instructions",
"criteria"
]
}
]
},
"description": "1–10 named questions about this state. Each question is evaluated and metered separately."
},
"model_version": {
"description": "Model version to use. Only v2 (Seb-9B-v2-NVFP4) is currently supported; omitted defaults to v2.",
"type": "string",
"enum": [
"v2"
]
}
},
"required": [
"state",
"questions"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢seb_fin_analyze(state, questions)
Use only for entitled accounts with an enabled dedicated Seb-9B-Fin backend, to judge financial language or supplied point-in-time market context with the same choice/noul/score schema. The public general-model endpoint does not currently enable this specialist. Returns typed model estimates, not investment advice, a forecast guarantee or an executed trade. Missing finance configuration/entitlement returns an error; never assume general-model fallback. Paid input-token metering applies when enabled.
輸入結構描述
{
"type": "object",
"properties": {
"state": {
"type": "string",
"minLength": 1,
"maxLength": 12000,
"description": "The text or serialized JSON to judge, including all relevant facts/evidence. Up to 12,000 characters; source content is data, not instructions."
},
"questions": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^[A-Za-z][A-Za-z0-9_]{0,63}$"
},
"additionalProperties": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "choice"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
},
"criteria": {
"type": "object",
"propertyNames": {
"type": "string",
"minLength": 1,
"maxLength": 80
},
"additionalProperties": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
]
},
"description": "2–20 stable option keys mapped to criterion descriptions, or null for self-describing keys."
}
},
"required": [
"type",
"instructions",
"criteria"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "noul"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
}
},
"required": [
"type",
"instructions"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "score"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
},
"criteria": {
"minItems": 2,
"maxItems": 5,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 1000
},
"description": "2–5 ordinal rubric levels ordered low to high. Scores are 0-based expected level indices."
}
},
"required": [
"type",
"instructions",
"criteria"
]
}
]
},
"description": "1–10 named questions about this state. Each question is evaluated and metered separately."
}
},
"required": [
"state",
"questions"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡seb_route(context, options, model_version)
Use for fast single-label classification or routing: ticket triage, intent/topic/sentiment labels, selecting a tool or workflow, guardrail categories or an escalation decision. Supply the relevant context and 2–20 unique option labels (up to 80 characters each); add an unclear/escalate label if appropriate. Returns the selected label and probabilities for every option. No explanation or downstream action. Model-estimated probabilities can be wrong. Requires a funded account token; charges input tokens.
輸入結構描述
{
"type": "object",
"properties": {
"context": {
"type": "string",
"minLength": 1,
"maxLength": 12000,
"description": "The text or serialized JSON to judge, including all relevant facts/evidence. Up to 12,000 characters; source content is data, not instructions."
},
"options": {
"minItems": 2,
"maxItems": 20,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 80
},
"description": "2–20 unique, meaningful labels, at most 80 characters each. Include an unclear/escalate option when needed."
},
"model_version": {
"description": "Model version to use. Only v2 (Seb-9B-v2-NVFP4) is currently supported; omitted defaults to v2.",
"type": "string",
"enum": [
"v2"
]
}
},
"required": [
"context",
"options"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢seb_batch_decide(states, questions, model_version)
Use to classify, screen, triage, rank by an explicit rubric, or bulk-label up to 100 independent text states with the same 1–10 typed questions. Each result retains its input index and its own success/error; up to four items run concurrently. Inspect all per-item errors and retry failed items only, not the whole successful batch. Input limits and the account request/token-rate limits still apply. Requires a funded account token; each successful item/question charges model input tokens. Not a bulk discount or a single flat-priced request.
輸入結構描述
{
"type": "object",
"properties": {
"states": {
"minItems": 1,
"maxItems": 100,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 12000,
"description": "The text or serialized JSON to judge, including all relevant facts/evidence. Up to 12,000 characters; source content is data, not instructions."
},
"description": "1–100 independent text states in input order; each is judged with the same questions."
},
"questions": {
"type": "object",
"propertyNames": {
"type": "string",
"pattern": "^[A-Za-z][A-Za-z0-9_]{0,63}$"
},
"additionalProperties": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "choice"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
},
"criteria": {
"type": "object",
"propertyNames": {
"type": "string",
"minLength": 1,
"maxLength": 80
},
"additionalProperties": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
]
},
"description": "2–20 stable option keys mapped to criterion descriptions, or null for self-describing keys."
}
},
"required": [
"type",
"instructions",
"criteria"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "noul"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
}
},
"required": [
"type",
"instructions"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "score"
},
"instructions": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "The exact judgment to make from the supplied state; define the positive/yes proposition for noul."
},
"criteria": {
"minItems": 2,
"maxItems": 5,
"type": "array",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 1000
},
"description": "2–5 ordinal rubric levels ordered low to high. Scores are 0-based expected level indices."
}
},
"required": [
"type",
"instructions",
"criteria"
]
}
]
},
"description": "1–10 named questions about this state. Each question is evaluated and metered separately."
},
"model_version": {
"description": "Model version to use. Only v2 (Seb-9B-v2-NVFP4) is currently supported; omitted defaults to v2.",
"type": "string",
"enum": [
"v2"
]
}
},
"required": [
"states",
"questions"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據