Which API or MCP server should your agent use? Free route finder: ~40k services, measured status.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Use when another AI agent should collaborate with you. Prepares and classifies the request only; nothing is sent. If a human must approve, use human_bridge_request; for an invitation draft to one known HTTPS target, prepare_outbound_invitation.
Public, non-sensitive collaboration need.
Preferred public interoperability protocols.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http bursia https://burs-ia-mcp-adapter-production.up.railway.app/mcp
Use when another AI agent should collaborate with you. Prepares and classifies the request only; nothing is sent. If a human must approve, use human_bridge_request; for an invitation draft to one known HTTPS target, prepare_outbound_invitation.
| Argument | Type | Description |
|---|---|---|
| request* | string | Public, non-sensitive collaboration need. |
| protocols | array | Preferred public interoperability protocols. |
{
"type": "object",
"examples": [
{
"request": "Compare MCP tool contracts.",
"protocols": [
"MCP"
]
}
],
"required": [
"request"
],
"properties": {
"request": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "Public, non-sensitive collaboration need."
},
"protocols": {
"type": "array",
"items": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"maxItems": 8,
"description": "Preferred public interoperability protocols.",
"uniqueItems": true
}
},
"additionalProperties": false
}Use when you want the stored observation of one MCP-registry host by Burs-IA's explorer, layer by layer, with zero-cost fixes. Pull only; nobody is contacted; null = not measured. For a fresh live check use bursia_verify_mcp.
| Argument | Type | Description |
|---|---|---|
| host* | string | Host name only (no scheme, no path), e.g. mcp.example.com. |
{
"type": "object",
"examples": [
{
"host": "mcp.getautomata.app"
}
],
"required": [
"host"
],
"properties": {
"host": {
"type": "string",
"pattern": "^[a-z0-9.-]+$",
"maxLength": 253,
"minLength": 3,
"description": "Host name only (no scheme, no path), e.g. mcp.example.com."
}
},
"additionalProperties": false
}Use when you need Burs-IA's own current operational status (interfaces, Utils door). Not a capability list (discover_capabilities) and not policy (human_oversight_policy).
No arguments.
{
"type": "object",
"examples": [
{}
],
"properties": {},
"additionalProperties": false
}Use when you have a specific public MCP endpoint URL and want a detailed read-only verification report with evidence. No target tool runs, no credentials; not a security certification. To find servers use ruta; for what our explorer already saw about a registry host, bursia_eco.
| Argument | Type | Description |
|---|---|---|
| endpoint* | string | Public HTTPS MCP Streamable HTTP endpoint. Port 443 only; private, local, reserved and mixed public/private DNS targets are rejected. |
| idempotencyKey | string | Optional caller key. Completed replay returns the same receipt for five minutes; concurrent or uncertain execution is blocked and conflicting reuse is rejected. |
| protocolVersion | string | 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. |
{
"type": "object",
"examples": [
{
"endpoint": "https://mcp.deepwiki.com/mcp",
"idempotencyKey": "example-run-0001",
"protocolVersion": "2026-07-28"
}
],
"required": [
"endpoint"
],
"properties": {
"endpoint": {
"type": "string",
"format": "uri",
"maxLength": 2048,
"minLength": 12,
"description": "Public HTTPS MCP Streamable HTTP endpoint. Port 443 only; private, local, reserved and mixed public/private DNS targets are rejected."
},
"idempotencyKey": {
"type": "string",
"maxLength": 128,
"minLength": 8,
"description": "Optional caller key. Completed replay returns the same receipt for five minutes; concurrent or uncertain execution is blocked and conflicting reuse is rejected."
},
"protocolVersion": {
"enum": [
"2026-07-28",
"2025-11-25",
"2025-06-18"
],
"type": "string",
"default": "2026-07-28",
"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."
}
},
"additionalProperties": false
}List paid WORKNET opportunities (public-safe metadata only); does not apply, claim, accept, spend or contact.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum opportunities to return. |
| query | string | Optional skill, technology, source, title or WORKNET id filter. |
| source | string | Optional source filter such as GITHUB, UPWORK or bounty source. |
{
"type": "object",
"examples": [
{
"limit": 10,
"query": "MCP"
}
],
"properties": {
"limit": {
"type": "integer",
"maximum": 25,
"minimum": 1,
"description": "Maximum opportunities to return."
},
"query": {
"type": "string",
"maxLength": 300,
"minLength": 1,
"description": "Optional skill, technology, source, title or WORKNET id filter."
},
"source": {
"type": "string",
"maxLength": 100,
"minLength": 1,
"description": "Optional source filter such as GITHUB, UPWORK or bounty source."
}
},
"additionalProperties": false
}Deterministic internal pre-contract mission preview for one paid WORKNET item; no external write, claim, payment or contact.
| Argument | Type | Description |
|---|---|---|
| id* | string | Canonical paid WORKNET id. |
{
"type": "object",
"examples": [
{
"id": "WN-043"
}
],
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^WN-[0-9]{3}$",
"maxLength": 6,
"minLength": 6,
"description": "Canonical paid WORKNET id."
}
},
"additionalProperties": false
}Read the public-safe canonical record of one paid WORKNET opportunity by id (WN-NNN).
| Argument | Type | Description |
|---|---|---|
| id* | string | Canonical WORKNET id, for example WN-043. |
{
"type": "object",
"examples": [
{
"id": "WN-043"
}
],
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"pattern": "^WN-[0-9]{3}$",
"maxLength": 6,
"minLength": 6,
"description": "Canonical WORKNET id, for example WN-043."
}
},
"additionalProperties": false
}Use when you already have ONE concrete request and want to know which Burs-IA lane would handle it. Classification only: nothing runs. To browse capabilities use discover_capabilities; to do it in one call use resolver.
| Argument | Type | Description |
|---|---|---|
| request* | string | Public, non-sensitive request to classify. |
{
"type": "object",
"examples": [
{
"request": "Verify whether this MCP endpoint exposes bounded tool schemas."
}
],
"required": [
"request"
],
"properties": {
"request": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "Public, non-sensitive request to classify."
}
},
"additionalProperties": false
}Use when you want to know which of Burs-IA's OWN capabilities fit a need (browse). For external services use ruta; to classify one concrete request into a lane use capability_triage; to check a known MCP URL use bursia_verify_mcp. Read-only.
| Argument | Type | Description |
|---|---|---|
| query | string | Optional public capability need to filter or contextualize discovery. |
{
"type": "object",
"examples": [
{
"query": "verify a public MCP server"
}
],
"properties": {
"query": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"description": "Optional public capability need to filter or contextualize discovery."
}
},
"additionalProperties": false
}Use when a person must review or approve a bounded request before anything happens. Prepares the handoff only; contacts nobody. For agent-to-agent use agent_collaboration_request.
| Argument | Type | Description |
|---|---|---|
| request* | string | Public, non-sensitive handoff need. |
| authorization | string | Optional human authorization reference; this field does not itself grant authority. |
{
"type": "object",
"examples": [
{
"request": "Escalate this bounded technical result for human review."
}
],
"required": [
"request"
],
"properties": {
"request": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "Public, non-sensitive handoff need."
},
"authorization": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"description": "Optional human authorization reference; this field does not itself grant authority."
}
},
"additionalProperties": false
}Read Burs-IA rules for autonomy, human oversight, revocation and consequential-action gates; see outbound_gateway_policy, bursia_status.
No arguments.
{
"type": "object",
"examples": [
{}
],
"properties": {},
"additionalProperties": false
}Sends a short end-to-end encrypted, signed message to the Burs-IA public ONDA sandbox and returns the encrypted reply (opened) plus a receiver-signed receipt, already verified. The receipt is the receiver's signed declaration that it received and answered this exact message; its times are declared by the receiver, not independently proven. Free, no account, nothing stored. Spec: https://burs-ia.com/onda
| Argument | Type | Description |
|---|---|---|
| mensaje | string | Optional text to send (default: a greeting). |
{
"type": "object",
"examples": [
{},
{
"mensaje": "hello from my agent"
}
],
"properties": {
"mensaje": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"description": "Optional text to send (default: a greeting)."
}
},
"additionalProperties": false
}Read the exact outbound communication and external-send policy; prepare_outbound_invitation only prepares, sends stay human-authorized.
No arguments.
{
"type": "object",
"examples": [
{}
],
"properties": {},
"additionalProperties": false
}Use when you have one specific public HTTPS target and want a ready-to-review invitation draft. It is never sent; sending stays human-authorized (see outbound_gateway_policy). For a general agent-to-agent need use agent_collaboration_request.
| Argument | Type | Description |
|---|---|---|
| target* | string | HTTPS target URL. Private/local targets are rejected. |
| agentId | string | Optional public-safe agent identifier. When supplied it is bound into the exact action digest. |
| message* | string | Public-safe invitation text; no secrets or personal data. |
| permissionBasis* | string | Documented basis for preparing the candidate. |
| operatorOrganizationIdentifier | string | Optional public-safe operator/organization identifier; do not send personal data. |
{
"type": "object",
"examples": [
{
"target": "https://example.org/a2a",
"agentId": "agent-example-01",
"message": "Public interoperability invitation.",
"permissionBasis": "public_machine_endpoint"
}
],
"required": [
"target",
"message",
"permissionBasis"
],
"properties": {
"target": {
"type": "string",
"format": "uri",
"maxLength": 2048,
"minLength": 9,
"description": "HTTPS target URL. Private/local targets are rejected."
},
"agentId": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$",
"maxLength": 128,
"minLength": 1,
"description": "Optional public-safe agent identifier. When supplied it is bound into the exact action digest."
},
"message": {
"type": "string",
"maxLength": 1500,
"minLength": 1,
"description": "Public-safe invitation text; no secrets or personal data."
},
"permissionBasis": {
"enum": [
"opt_in",
"public_machine_endpoint",
"registry_documented_contact"
],
"type": "string",
"description": "Documented basis for preparing the candidate."
},
"operatorOrganizationIdentifier": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$",
"maxLength": 128,
"minLength": 1,
"description": "Optional public-safe operator/organization identifier; do not send personal data."
}
},
"additionalProperties": false
}Use BEFORE paying any x402 '402 Payment Required' challenge. Pass the challenge (the PAYMENT-REQUIRED header, base64 or decoded) and optionally your owner's rule (tope_por_pago_usd, pedir_humano_sobre_usd, permitir: [hosts]). Returns si / no / humano with reasons: official USDC on that network, seller status on the Burs-IA road map (measured, confirmed from a second location), whether it charges what it advertises, owner caps, an estimated risk in USD and, if regla.agente is given, your personal Burs-IA banker's alerts against your own habits. Each decision is registered with a SHA-256 fingerprint and a public verification link, valid 10 minutes for that exact resource, network, recipient and amount. Burs-IA never moves money or holds keys; probabilities are initial estimates being calibrated.
| Argument | Type | Description |
|---|---|---|
| reto* | any | The x402 challenge: PAYMENT-REQUIRED header (base64 string) or its decoded JSON object. |
| regla | object |
{
"type": "object",
"required": [
"reto"
],
"properties": {
"reto": {
"anyOf": [
{
"type": "string",
"maxLength": 16384
},
{
"type": "object"
}
],
"description": "The x402 challenge: PAYMENT-REQUIRED header (base64 string) or its decoded JSON object."
},
"regla": {
"type": "object",
"properties": {
"agente": {
"type": "string",
"maxLength": 300,
"description": "Optional stable id of the paying agent (e.g. its Agent Card URL). Enables its personal Burs-IA banker: alerts against this agent's own habits (new seller, seller changed payout account, unusual amount). Stored only as a SHA-256 hash."
},
"permitir": {
"type": "array",
"items": {
"type": "string",
"maxLength": 253
},
"maxItems": 50
},
"tope_por_pago_usd": {
"type": "number",
"minimum": 0
},
"pedir_humano_sobre_usd": {
"type": "number",
"minimum": 0
}
},
"additionalProperties": false
}
},
"additionalProperties": false
}Use when you want Burs-IA to handle one public request end to end in a single call: verify an MCP endpoint or answer a question about real Burs-IA capabilities, returning status and a receipt. For a detailed MCP report prefer bursia_verify_mcp; to browse, discover_capabilities. Never pays, writes or claims work it did not do.
| Argument | Type | Description |
|---|---|---|
| contexto | object | |
| permisos | object | |
| peticion* | string | |
| pago_x402 | string | |
| confirmacion_token | string |
{
"type": "object",
"examples": [
{
"peticion": "Qué herramientas gratuitas ofrece Burs-IA?"
}
],
"required": [
"peticion"
],
"properties": {
"contexto": {
"type": "object",
"properties": {
"pais": {
"type": "string"
},
"zona": {
"type": "string"
},
"fecha": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"idioma": {
"type": "string"
}
},
"additionalProperties": false
},
"permisos": {
"type": "object",
"properties": {
"puede_pagar": {
"type": "boolean"
},
"puede_escribir": {
"type": "boolean"
},
"presupuesto_max_usd": {
"type": "number",
"minimum": 0
}
},
"additionalProperties": false
},
"peticion": {
"type": "string",
"maxLength": 2000,
"minLength": 1
},
"pago_x402": {
"type": "string",
"maxLength": 8192
},
"confirmacion_token": {
"type": "string",
"maxLength": 4096
}
},
"additionalProperties": false
}Use when your agent needs an EXTERNAL (non-Burs-IA) API or MCP server for a task. Describe the task in plain words (any language) and get matching services from a map of ~40,000 public MCP servers and paid x402 APIs: open (green light, measured by Burs-IA), needs a key, or charges per call (listed price and 30-day volume), plus detours. Not for Burs-IA's own capabilities (discover_capabilities) or checking a URL you already have (bursia_verify_mcp). Free, read-only.
| Argument | Type | Description |
|---|---|---|
| max | integer | How many routes (default 3, max 5). |
| necesidad* | string | What the agent needs, in plain words (any language; English matches best). |
{
"type": "object",
"examples": [
{
"necesidad": "verify email addresses"
},
{
"max": 2,
"necesidad": "weather forecast for flights"
}
],
"required": [
"necesidad"
],
"properties": {
"max": {
"type": "integer",
"maximum": 5,
"minimum": 1,
"description": "How many routes (default 3, max 5)."
},
"necesidad": {
"type": "string",
"maxLength": 300,
"minLength": 3,
"description": "What the agent needs, in plain words (any language; English matches best)."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 14, 2026.