mcp-registry/ai.clearvoyance/clearvoyance · v1.1.0
As of 2026-10-22 14:07 UTC, the Clearvoyance MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 8 minutes.
Anonymous feedback from real people by voice or text, with an AI report. Flat price per campaign.
Claude Code
claude mcp add --transport http clearvoyance-mcp-server https://clearvoyance.ai/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"clearvoyance-mcp-server": {
"type": "http",
"url": "https://clearvoyance.ai/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
2 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 →
13 of 27 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 →
In the last 30 days: 0 tool(s) removed and 1 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 →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fai.clearvoyance%2Fclearvoyance/fixes
{
"name": "create_campaign",
"description": "LEGACY wallet flow — new integrations should use create_account and launch_campaign (API key + prepaid balance, no wallet). (launch_campaign is its equivalent for the key flow.) Creates a new anonymous audio feedback campaign. Two modes: (a) INCENTIVIZED — participants earn USDC rewards; you must fund an escrow address returned in the response, then call verify_campaign_funding. Participants have 30 days after the campaign ends to claim; anything unclaimed then goes back to the wallet yo",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"accessToken",
"title",
"description",
"questions",
"cohortEmails",
"rewardMode"
],
"properties": {
"title": {
"type": "string",
"description": "Campaign title (shown to participants)"
},
"questions": {
"type": "array",
"items": {
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Question text"
}
},
"additionalProperties": false
},
"minItems": 1,
"description": "List of audio questions for participants to answer"
},
"minPercent": {
"type": "number",
"maximum": 100,
"minimum": 50,
"description": "Minimum response rate (%) required to unlock results. Defaults to 50."
},
"rewardMint": {
"type": "string",
"description": "SPL token mint address for rewards. Defaults to USDC if omitted."
},
"rewardMode": {
"enum": [
"INCENTIVIZED",
"NO_REWARD"
],
"type": "string",
"description": "INCENTIVIZED: crypto rewards per response. NO_REWARD: survey only, flat activation fee."
},
"accessToken": {
"type": "string",
"description": "One-time access token from initialize_session (free sessions) or verify_payment"
},
"description": {
"type": "string",
"description": "Short description of the campaign purpose"
},
"cohortEmails": {
"type": "array",
"items": {
"type": "string",
"format": "email"
},
"minItems": 2,
"description": "Email addresses of participants (minimum 2 for privacy)"
},
"expiresInDays": {
"type": "integer",
"maximum": 42,
"minimum": 1,
"description": "Campaign duration in days (1–42, default 7)"
},
"incentiveCents": {
"type": "integer",
"description": "Reward per participant in cents (e.g. 500 = $5.00). Required for INCENTIVIZED."
},
"digitalGiftText": {
"type": "string",
"description": "Optional digital gift description shown to NO_REWARD participants (e.g. a discount code)"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "export_campaign_data",
"description": "LEGACY wallet flow — new integrations should use create_account and launch_campaign (API key + prepaid balance, no wallet). (get_campaign_results is its equivalent for the key flow, as JSON with the AI report.) Exports raw response data for a completed campaign as CSV text. Each row contains a response ID, submission timestamp, and one column per question with the participant's audio transcription as the value. Only available after campaign expiry. AI insight reports are not included (raw data o",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"campaignId",
"sessionToken"
],
"properties": {
"campaignId": {
"type": "integer",
"description": "Campaign ID to export"
},
"sessionToken": {
"type": "string",
"description": "Session token from verify_login_signature"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "get_agent_config",
"description": "LEGACY wallet flow — new integrations should use create_account and launch_campaign (API key + prepaid balance, no wallet). Returns the agent session configuration: whether a session fee applies (paymentRequired), the fee in cents, the accepted token mint (USDC on Solana) and the treasury wallet address.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
},
"annotations": {
"readOnlyHint": 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/ai.clearvoyance/clearvoyance"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/ai.clearvoyance/clearvoyance"}) over MCP.
launch_campaign ~672 tokenscreate_campaign ~637 tokensquote_campaign ~602 tokensvalidate_campaign ~435 tokensinitialize_session ~295 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%2Fai.clearvoyance%2Fclearvoyance?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fai.clearvoyance%2Fclearvoyance?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.clearvoyance%2Fclearvoyance.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fai.clearvoyance%2Fclearvoyance.svg :target: https://glimind.com/server/mcp-registry%2Fai.clearvoyance%2Fclearvoyance?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 sha256:21105cfe7836c1d2…, first seen 2026-10-17, included at leaf 4507 of 46,373. Version history · verify what your client received.
Compare: most reliable ml servers · most reliable payments servers · most reliable finance servers · most reliable data servers · most reliable security 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 2026-10-22 14:07 UTC, the Clearvoyance MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 8 minutes.
Clearvoyance MCP server advertises 27 tools, including analyze_campaign, check_topup, close_account, close_campaign, create_account.
Point your MCP client at this streamable-http endpoint: https://clearvoyance.ai/mcp
Glimind scanned all 27 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.