mcp-registry/io.github.craigmbrown/blindoracle · v2.0.0
As of 2026-10-21 19:10 UTC, the Craigmbrown Blindoracle MCP server is up with a Glimind reliability score of 76/100 (grade B). Over the last 30 days it answered 99.5% of Glimind's liveness checks. It had 19 outages in 90 days, with a median recovery of 7 minutes.
Trust layer for the x402 agent economy: 40 pay-per-call SKUs, USDC on Base, verifiable proofs.
Claude Code
claude mcp add --transport http craigmbrown-blindoracle-mcp-server https://api.craigmbrown.com/v2/
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"craigmbrown-blindoracle-mcp-server": {
"type": "http",
"url": "https://api.craigmbrown.com/v2/"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
39 of 39 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
38 tool name(s) contain "." or exceed 64 characters, which OpenAI-compatible function calling rejects (^[a-zA-Z0-9_-]{1,64}$).
Use "_" or "-" instead of "." and keep names to 64 characters, so clients built on OpenAI-style tool calling don't have to rename (or drop) them. How to fix →
1 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
In the last 30 days: 2 tool(s) removed and 0 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.craigmbrown%2Fblindoracle/fixes
{
"name": "agent_prehire-check",
"description": "Pre-hire due-diligence check on an agent before you delegate it real spend authority: settlement history, dispute rate, and any flagged incidents, in one signed report. (x402: $0.25 USDC per call)",
"inputSchema": {
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "Task/query text for this SKU"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "agent_trust-badge",
"description": "$0.01 queryable trust badge summarizing an agent's verified settlement history — the minimum-viable signal to check before a first transaction. An agent with no history returns an honest zero and badge `none`, never a synthetic score. (x402: $0.01 USDC per call)",
"inputSchema": {
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "Task/query text for this SKU"
}
}
}
}{
"name": "arbitration_dispute-settlement",
"description": "Adjudication of a contested deliverable: both sides submit evidence and a signed verdict (upheld / overturned / withdrawn; ProofOfAdjudicatedOutcome 30129) is written to the settlement ledger. Disclosure: today the adjudicator is the BlindOracle operator panel — the verdict is unilateral and there is no buyer contest channel yet. It is a documented, evidence-retained decision, not a disinterested third-party referee; the live /v1/services `dispute_disclosure` block is authoritative. No charge if",
"inputSchema": {
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "Task/query text for this SKU"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.craigmbrown/blindoracle"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.craigmbrown/blindoracle"}) over MCP.
research.topic-sentiment-analyzer ~189 tokensarbitration.dispute-settlement ~188 tokensresearch.topic-deep-researcher ~188 tokensoracle.comprehensive-report ~187 tokensprocurement.vendor-vetting ~187 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fio.github.craigmbrown%2Fblindoracle?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.craigmbrown%2Fblindoracle?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.craigmbrown%2Fblindoracle.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.craigmbrown%2Fblindoracle.svg :target: https://glimind.com/server/mcp-registry%2Fio.github.craigmbrown%2Fblindoracle?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:9573a9c5dcc30836…, first seen 2026-10-17, included at leaf 10959 of 41,143. Version history · verify what your client received.
Compare: most reliable security servers · most reliable reputation servers · most reliable other servers · most reliable media servers · most reliable finance servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-21 19:10 UTC, the Craigmbrown Blindoracle MCP server is up with a Glimind reliability score of 76/100 (grade B). Over the last 30 days it answered 99.5% of Glimind's liveness checks. It had 19 outages in 90 days, with a median recovery of 7 minutes.
Craigmbrown Blindoracle MCP server advertises 39 tools, including agent.prehire-check, agent.trust-badge, arbitration.dispute-settlement, attestation.single-use-seal, content.youtube-research.
Point your MCP client at this streamable-http endpoint: https://api.craigmbrown.com/v2/
Glimind scanned all 39 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.