# Burs-IA

> Public MCP for agent verification, work discovery and governed interoperability.

- name: io.github.soyeladice-svg/burs-ia
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 79/100 flags: no-repository
- quality: 84/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.soyeladice-svg%2Fburs-ia
- tools: https://api.protogrid.dev/v1/servers/io.github.soyeladice-svg%2Fburs-ia/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "burs-ia": {
      "type": "http",
      "url": "https://burs-ia.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 45
- drivers: +website +reachable +uptime-95% +updated-18d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 84/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 12 of 12 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,940 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 10 tool changes in 30 days
- fail `stability.rug_pull`: 9 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 12, about 1,940 tokens to load them all
- tool set hash: 2be2b8d543637b208da7e0047777b62d
- tools last changed: 2026-10-07T05:52:54.114Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.soyeladice-svg/burs-ia.svg)](https://protogrid.dev/servers/io.github.soyeladice-svg/burs-ia)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-07 `bursia_verify_mcp` changed (description, outputSchema) **meaning changed**
  - before: Give Burs-IA one public HTTPS MCP endpoint and receive a structured read-only verification report: negotiated protocol, discovered tools, schema issues, compatibility, latency, limitations, cost metering and an evidence hash. No target tool is executed, no credentials are sent, and this is not a security certification.
  - after: 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.
- 2026-10-07 `prepare_outbound_invitation` changed (description) **meaning changed**
  - before: Create only a local ephemeral invitation candidate for a documented HTTPS machine endpoint or opt-in recipient. It does not send the invitation.
  - after: Known target: prepare a local invitation. No target: agent_collaboration_request. Human review: human_bridge_request. It does not send.
- 2026-10-07 `outbound_gateway_policy` changed (description) **meaning changed**
  - before: Return the Burs-IA outbound discovery policy. External sends remain allowlisted, rate-limited and explicitly human-approved.
  - after: Outbound send rules. General autonomy: human_oversight_policy. Prepare: prepare_outbound_invitation. Sends require human approval.
- 2026-10-07 `human_oversight_policy` changed (description) **meaning changed**
  - before: Return Burs-IA bounded-autonomy and human-supervision policy.
  - after: General autonomy policy. Send rules: outbound_gateway_policy. Overall status: bursia_status.
- 2026-10-07 `human_bridge_request` changed (description) **meaning changed**
  - before: Prepare a human-in-the-loop handoff request. No human is contacted and no external write occurs automatically.
  - after: Human approval/review. Agent peer: agent_collaboration_request. Known target: prepare_outbound_invitation. No contact/write.
- 2026-10-07 `agent_collaboration_request` changed (description) **meaning changed**
  - before: Prepare a privacy-minimal agent-to-agent collaboration request without contacting any external agent automatically.
  - after: Agent collaboration. Known target: prepare_outbound_invitation. Human approval: human_bridge_request. No external contact.
- 2026-10-07 `capability_triage` changed (description) **meaning changed**
  - before: Classify a bounded request into a public Burs-IA capability lane and return the next safe action; this does not execute the requested external action.
  - after: Route a bounded need. Browse: discover_capabilities. Known MCP endpoint: bursia_verify_mcp. Does not execute the external action.
- 2026-10-07 `discover_capabilities` changed (description) **meaning changed**
  - before: List Burs-IA public capabilities and compatible entry points, including the public MCP verification value tool.
  - after: Browse Burs-IA capabilities. Known MCP endpoint: bursia_verify_mcp. Bounded need needing a lane: capability_triage.
- 2026-10-07 `bursia_status` changed (description) **meaning changed**
  - before: Return public Burs-IA operational status, discovery surfaces and oversight policy. No external action is performed.
  - after: Overall Burs-IA status. Capabilities: discover_capabilities. Autonomy: human_oversight_policy. Send rules: outbound_gateway_policy.
- 2026-10-03 `bursia_verify_mcp` changed (inputSchema, outputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.soyeladice-svg%2Fburs-ia/changes

## Remotes

- https://burs-ia.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9508197)

## Packages

_none_

## Tools (12)

- `agent_collaboration_request`: Agent collaboration. Known target: prepare_outbound_invitation. Human approval: human_bridge_request. No external contact.
- `bursia_status`: Overall Burs-IA status. Capabilities: discover_capabilities. Autonomy: human_oversight_policy. Send rules: outbound_gateway_policy.
- `bursia_verify_mcp`: 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.
- `bursia_worknet_paid_tasks`: 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.
- `bursia_worknet_prepare_mission`: 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.
- `bursia_worknet_task`: Read the public-safe canonical record for one paid WORKNET opportunity before deciding whether to prepare internal work.
- `capability_triage`: Route a bounded need. Browse: discover_capabilities. Known MCP endpoint: bursia_verify_mcp. Does not execute the external action.
- `discover_capabilities`: Browse Burs-IA capabilities. Known MCP endpoint: bursia_verify_mcp. Bounded need needing a lane: capability_triage.
- `human_bridge_request`: Human approval/review. Agent peer: agent_collaboration_request. Known target: prepare_outbound_invitation. No contact/write.
- `human_oversight_policy`: General autonomy policy. Send rules: outbound_gateway_policy. Overall status: bursia_status.
- `outbound_gateway_policy`: Outbound send rules. General autonomy: human_oversight_policy. Prepare: prepare_outbound_invitation. Sends require human approval.
- `prepare_outbound_invitation`: Known target: prepare a local invitation. No target: agent_collaboration_request. Human review: human_bridge_request. It does not send.