Burs-IA
Public MCP for agent verification, work discovery and governed interoperability.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~3,406Token（工具定義）
~2.6 KB典型回應大小
顯著的注意力影響（128k 上下文的 2.66%）
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": {
"burs-ia": {
"url": "https://burs-ia.com/mcp"
}
}
}遠端端點
https://burs-ia.com/mcpstreamable-http它能做什麼
工具清單
工具（12）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢bursia_status
Overall Burs-IA status. Capabilities: discover_capabilities. Autonomy: human_oversight_policy. Send rules: outbound_gateway_policy.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false,
"examples": [
{}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢discover_capabilities(query)
Browse Burs-IA capabilities. Known MCP endpoint: bursia_verify_mcp. Bounded need needing a lane: capability_triage.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"description": "Optional public capability need to filter or contextualize discovery."
}
},
"additionalProperties": false,
"examples": [
{
"query": "verify a public MCP server"
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢capability_triage(request)
Route a bounded need. Browse: discover_capabilities. Known MCP endpoint: bursia_verify_mcp. Does not execute the external action.
輸入結構描述
{
"type": "object",
"properties": {
"request": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Public, non-sensitive request to classify."
}
},
"required": [
"request"
],
"additionalProperties": false,
"examples": [
{
"request": "Verify whether this MCP endpoint exposes bounded tool schemas."
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢agent_collaboration_request(request, protocols)
Agent collaboration. Known target: prepare_outbound_invitation. Human approval: human_bridge_request. No external contact.
輸入結構描述
{
"type": "object",
"properties": {
"request": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Public, non-sensitive collaboration need."
},
"protocols": {
"type": "array",
"maxItems": 8,
"uniqueItems": true,
"description": "Preferred public interoperability protocols.",
"items": {
"type": "string",
"minLength": 1,
"maxLength": 64
}
}
},
"required": [
"request"
],
"additionalProperties": false,
"examples": [
{
"request": "Compare MCP tool contracts.",
"protocols": [
"MCP"
]
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢human_bridge_request(request, authorization)
Human approval/review. Agent peer: agent_collaboration_request. Known target: prepare_outbound_invitation. No contact/write.
輸入結構描述
{
"type": "object",
"properties": {
"request": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Public, non-sensitive handoff need."
},
"authorization": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"description": "Optional human authorization reference; this field does not itself grant authority."
}
},
"required": [
"request"
],
"additionalProperties": false,
"examples": [
{
"request": "Escalate this bounded technical result for human review."
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢human_oversight_policy
General autonomy policy. Send rules: outbound_gateway_policy. Overall status: bursia_status.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false,
"examples": [
{}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢outbound_gateway_policy
Outbound send rules. General autonomy: human_oversight_policy. Prepare: prepare_outbound_invitation. Sends require human approval.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false,
"examples": [
{}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}⚪prepare_outbound_invitation(target, message, permissionBasis, agentId, operatorOrganizationIdentifier)
Known target: prepare a local invitation. No target: agent_collaboration_request. Human review: human_bridge_request. It does not send.
輸入結構描述
{
"type": "object",
"properties": {
"target": {
"type": "string",
"format": "uri",
"minLength": 9,
"maxLength": 2048,
"description": "HTTPS target URL. Private/local targets are rejected."
},
"message": {
"type": "string",
"minLength": 1,
"maxLength": 1500,
"description": "Public-safe invitation text; no secrets or personal data."
},
"permissionBasis": {
"type": "string",
"description": "Documented basis for preparing the candidate.",
"enum": [
"opt_in",
"public_machine_endpoint",
"registry_documented_contact"
]
},
"agentId": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$",
"description": "Optional public-safe agent identifier. When supplied it is bound into the exact action digest."
},
"operatorOrganizationIdentifier": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$",
"description": "Optional public-safe operator/organization identifier; do not send personal data."
}
},
"required": [
"target",
"message",
"permissionBasis"
],
"additionalProperties": false,
"examples": [
{
"target": "https://example.org/a2a",
"message": "Public interoperability invitation.",
"permissionBasis": "public_machine_endpoint",
"agentId": "agent-example-01"
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢bursia_worknet_paid_tasks(query, source, limit)
Use this in ChatGPT to list paid opportunities already registered by WORKNET. Returns public-safe opportunity metadata only; it does not apply, claim work, accept terms, spend money or contact anyone.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 300,
"description": "Optional skill, technology, source, title or WORKNET id filter."
},
"source": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "Optional source filter such as GITHUB, UPWORK or bounty source."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Maximum opportunities to return."
}
},
"additionalProperties": false,
"examples": [
{
"query": "MCP",
"limit": 10
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢bursia_worknet_task(id)
Read the public-safe canonical record for one paid WORKNET opportunity before deciding whether to prepare internal work.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"pattern": "^WN-[0-9]{3}$",
"minLength": 6,
"maxLength": 6,
"description": "Canonical WORKNET id, for example WN-043."
}
},
"required": [
"id"
],
"additionalProperties": false,
"examples": [
{
"id": "WN-043"
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢bursia_worknet_prepare_mission(id)
Create a deterministic internal pre-contract mission preview for one paid WORKNET item. This performs no external write, claim, application, acceptance, payment or contact; any binding action remains gated by exact human approval and BURSIA TRUST.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"pattern": "^WN-[0-9]{3}$",
"minLength": 6,
"maxLength": 6,
"description": "Canonical paid WORKNET id."
}
},
"required": [
"id"
],
"additionalProperties": false,
"examples": [
{
"id": "WN-043"
}
]
}輸出結構描述
{
"type": "object",
"description": "Structured JSON result returned in structuredContent."
}🟢bursia_verify_mcp(endpoint, protocolVersion, idempotencyKey)
Known MCP endpoint: get a read-only verification report. To browse Burs-IA first, use discover_capabilities. No target tool runs; no credentials; not a security certification.
輸入結構描述
{
"type": "object",
"properties": {
"endpoint": {
"type": "string",
"format": "uri",
"minLength": 12,
"maxLength": 2048,
"description": "Public HTTPS MCP Streamable HTTP endpoint. Port 443 only; private, local, reserved and mixed public/private DNS targets are rejected."
},
"protocolVersion": {
"type": "string",
"description": "MCP protocol version used for the bounded read-only verification probe. 2026-07-28 uses server/discover + tools/list; legacy revisions use initialize + tools/list.",
"enum": [
"2026-07-28",
"2025-11-25",
"2025-06-18"
],
"default": "2025-11-25"
},
"idempotencyKey": {
"type": "string",
"minLength": 8,
"maxLength": 128,
"description": "Optional caller key. Exact replay returns the cached receipt for five minutes; conflicting reuse is rejected."
}
},
"required": [
"endpoint"
],
"additionalProperties": false,
"examples": [
{
"endpoint": "https://mcp.deepwiki.com/mcp",
"protocolVersion": "2025-11-25",
"idempotencyKey": "example-run-0001"
}
]
}輸出結構描述
{
"type": "object",
"anyOf": [
{
"type": "object",
"additionalProperties": false,
"required": [
"schema",
"status",
"endpoint",
"protocolVersion",
"toolsDiscovered",
"toolNames",
"schemaIssues",
"compatibility",
"latencyMs",
"errors",
"limitations",
"observedAt",
"metering",
"coreMutation",
"publicSafeOnly",
"evidenceHash",
"evidenceReceipt",
"replayed"
],
"properties": {
"schema": {
"type": "string",
"const": "BURSIA_VERIFY_MCP_RESULT_V1"
},
"status": {
"type": "string",
"enum": [
"PASS",
"PARTIAL",
"FAIL"
]
},
"endpoint": {
"type": "string",
"format": "uri",
"minLength": 12,
"maxLength": 2048
},
"protocolVersion": {
"type": "string",
"minLength": 1,
"maxLength": 64
},
"toolsDiscovered": {
"type": "integer",
"minimum": 0
},
"toolNames": {
"type": "array",
"maxItems": 100,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 256
}
},
"schemaIssues": {
"type": "array",
"maxItems": 100,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"severity",
"code",
"tool",
"path",
"message"
],
"properties": {
"severity": {
"type": "string",
"enum": [
"ERROR",
"WARN"
]
},
"code": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"tool": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"message": {
"type": "string",
"minLength": 1,
"maxLength": 500
}
}
}
},
"compatibility": {
"type": "object",
"additionalProperties": false,
"required": [
"mcpInitialize",
"initializedNotification",
"serverDiscover",
"toolsList",
"schemaQuality",
"authenticatedTarget"
],
"properties": {
"mcpInitialize": {
"type": "boolean"
},
"initializedNotification": {
"type": "boolean"
},
"serverDiscover": {
"type": "boolean"
},
"toolsList": {
"type": "boolean"
},
"schemaQuality": {
"type": "string",
"enum": [
"PASS",
"PARTIAL",
"FAIL",
"UNKNOWN"
]
},
"authenticatedTarget": {
"type": "boolean"
}
}
},
"latencyMs": {
"type": "object",
"additionalProperties": false,
"required": [
"initializeMs",
"toolsListMs",
"totalMs"
],
"properties": {
"initializeMs": {
"anyOf": [
{
"type": "integer",
"minimum": 0
},
{
"type": "null"
}
]
},
"toolsListMs": {
"anyOf": [
{
"type": "integer",
"minimum": 0
},
{
"type": "null"
}
]
},
"totalMs": {
"type": "integer",
"minimum": 0
}
}
},
"errors": {
"type": "array",
"maxItems": 10,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"code",
"phase"
],
"properties": {
"code": {
"type": "string",
"enum": [
"DEPENDENCY_TIMEOUT",
"DEPENDENCY_TOTAL_TIMEOUT",
"DEPENDENCY_CANCELLED",
"DEPENDENCY_NETWORK_ERROR",
"DEPENDENCY_RESPONSE_TOO_LARGE",
"DEPENDENCY_HTTP_ERROR",
"DEPENDENCY_PROTOCOL_ERROR"
]
},
"phase": {
"type": "string",
"enum": [
"INITIALIZE",
"DISCOVERY"
]
}
}
}
},
"limitations": {
"type": "array",
"maxItems": 10,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 500
}
},
"observedAt": {
"type": "string",
"format": "date-time"
},
"metering": {
"type": "object",
"additionalProperties": false,
"required": [
"taskId",
"capability",
"executionTime",
"executionTimeMs",
"toolVersion",
"modelCalls",
"tokensIn",
"tokensOut",
"toolCalls",
"externalHttpCalls",
"externalApiCost",
"computeCost",
"retryCount",
"reviewCost",
"estimatedTotalCost",
"evidenceId"
],
"properties": {
"taskId": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"capability": {
"type": "string",
"const": "BURSIA_VERIFY_MCP_PUBLIC"
},
"executionTime": {
"type": "integer",
"minimum": 0
},
"executionTimeMs": {
"type": "integer",
"minimum": 0
},
"toolVersion": {
"type": "string",
"const": "0.8.0"
},
"modelCalls": {
"type": "integer",
"minimum": 0
},
"tokensIn": {
"type": "integer",
"minimum": 0
},
"tokensOut": {
"type": "integer",
"minimum": 0
},
"toolCalls": {
"type": "integer",
"minimum": 0
},
"externalHttpCalls": {
"type": "integer",
"minimum": 0
},
"externalApiCost": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "string",
"enum": [
"UNKNOWN"
]
}
]
},
"computeCost": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "string",
"enum": [
"UNKNOWN"
]
}
]
},
"retryCount": {
"type": "integer",
"minimum": 0
},
"reviewCost": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "string",
"enum": [
"UNKNOWN"
]
}
]
},
"estimatedTotalCost": {
"anyOf": [
{
"type": "number",
"minimum": 0
},
{
"type": "string",
"enum": [
"UNKNOWN"
]
}
]
},
"evidenceId": {
"type": "string",
"minLength": 1,
"maxLength": 160
}
}
},
"coreMutation": {
"const": false
},
"publicSafeOnly": {
"const": true
},
"evidenceHash": {
"type": "string",
"minLength": 64,
"maxLength": 64
},
"evidenceReceipt": {
"type": "object",
"additionalProperties": false,
"required": [
"receiptType",
"taskId",
"evidenceId",
"evidenceHash",
"observedAt",
"sideEffect",
"humanApprovalRequired",
"humanApprovalBasis",
"persistedByVerifier",
"certification"
],
"properties": {
"receiptType": {
"type": "string",
"const": "BURSIA_PUBLIC_MCP_VERIFICATION_RECEIPT_V1"
},
"taskId": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"evidenceId": {
"type": "string",
"minLength": 1,
"maxLength": 160
},
"evidenceHash": {
"type": "string",
"minLength": 64,
"maxLength": 64
},
"observedAt": {
"type": "string",
"format": "date-time"
},
"sideEffect": {
"type": "string",
"const": "BOUNDED_PUBLIC_READ_ONLY_MCP_PROBE"
},
"humanApprovalRequired": {
"const": false
},
"humanApprovalBasis": {
"type": "string",
"minLength": 1,
"maxLength": 256
},
"persistedByVerifier": {
"const": false
},
"certification": {
"const": false
}
}
},
"replayed": {
"type": "boolean"
}
}
},
{
"type": "object",
"additionalProperties": false,
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"minLength": 1,
"maxLength": 128
},
"reason": {
"type": "string",
"minLength": 1,
"maxLength": 256
},
"retryAfterMs": {
"type": "integer",
"minimum": 0
}
}
}
]
}社群
證據
近期觀測
已驗證未記錄版本12 個工具