pulsemcp/finturb-analytics · v1.27.0
As of 2026-10-26 17:50 UTC, FinTurb Analytics is up with a Glimind reliability score of 88/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 7 outages in 90 days, with a median recovery of 5 minutes.
Delivers institutional-grade quantitative risk analytics, including composite risk scoring, systemic fragility monitoring, and global liquidity indices.
Point your MCP client at this streamable_http endpoint: https://mcp-mkic.pythonanywhere.com/mcp
70 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
111 parameter(s) across 43 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. 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 →
31 of 70 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 →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 43 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/pulsemcp%2Ffinturb-analytics/fixes
{
"name": "agent_pm_approve",
"description": "Agentic firm-simulation TOOL form — portfolio manager — final approve/reject/revise verdict with audit footer (Tier-1 in Phase A; Tier-2 wrapper in Phase B). Tool-callable wrapper around the matching @mcp.prompt of the same role. Use this from MCP hosts that cannot invoke prompts programmatically (e.g. claude.ai web tool_use blocks). The methodology lives at the resource `finturb://skills/agents/pm_approve` and MUST be read before producing output. Arguments: ticker (optional; defaults to 'Marke",
"inputSchema": {
"type": "object",
"title": "tool_agent_pm_approveArguments",
"properties": {
"as_of": {
"type": "string",
"title": "As Of",
"default": ""
},
"ticker": {
"type": "string",
"title": "Ticker",
"default": ""
},
"upstream_reports": {
"type": "string",
"title": "Upstream Reports",
"default": ""
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "agent_pm_validate_math",
"description": "Agentic firm-simulation TOOL form — arithmetic gate validator. Tool-callable wrapper for the pm_validate_math role. Use when claude.ai or other tool-only surfaces need to invoke pm_validate_math programmatically. The methodology lives at finturb://skills/agents/pm_validate_math and MUST be read before producing output.",
"inputSchema": {
"type": "object",
"title": "tool_agent_pm_validate_mathArguments",
"properties": {
"as_of": {
"type": "string",
"title": "As Of",
"default": ""
},
"ticker": {
"type": "string",
"title": "Ticker",
"default": ""
},
"upstream_reports": {
"type": "string",
"title": "Upstream Reports",
"default": ""
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "get_firm_bundle",
"description": "Run a full firm simulation in ONE fetch - returns the complete 10-stage run-book PLUS all 21 agent methodologies (9 analysts, catalyst graph, transmission analyst, fragility gate, bull/bear researchers, research manager, three-way risk panel, trader, math validator, PM) in a single payload. PREFER this over calling firm_simulation + individual agent_* tools whenever executing the whole pipeline: it replaces ~20 static-text fetches and prevents the tool-call-quota aborts seen on claude.ai web. In",
"inputSchema": {
"type": "object",
"title": "tool_get_firm_bundleArguments",
"required": [
"ticker"
],
"properties": {
"as_of": {
"type": "string",
"title": "As Of",
"default": ""
},
"ticker": {
"type": "string",
"title": "Ticker"
},
"mandate": {
"type": "string",
"title": "Mandate",
"default": "default-v1"
}
}
},
"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":["pulsemcp/finturb-analytics"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "pulsemcp/finturb-analytics"}) over MCP.
finalize_audit ~316 tokensfinalize_memo ~304 tokensagent_analyst_geopolitical_transmission ~241 tokensget_options_chain ~236 tokensagent_analyst_fundamentals ~234 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/pulsemcp%2Ffinturb-analytics?ref=badge)
<a href="https://glimind.com/server/pulsemcp%2Ffinturb-analytics?ref=badge"><img src="https://glimind.com/v1/readiness/badge/pulsemcp%2Ffinturb-analytics.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/pulsemcp%2Ffinturb-analytics.svg :target: https://glimind.com/server/pulsemcp%2Ffinturb-analytics?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 sha256:3875bd8caad4d1ba…, first seen 2026-10-17, included at leaf 3137 of 74,545. Version history · verify what your client received.
Compare: most reliable knowledge servers · most reliable other servers · most reliable ml servers · most reliable media servers · most reliable data 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 2026-10-26 17:50 UTC, FinTurb Analytics is up with a Glimind reliability score of 88/100 (grade B). Over the last 30 days it answered 99.9% of Glimind's liveness checks. It had 7 outages in 90 days, with a median recovery of 5 minutes.
FinTurb Analytics advertises 70 tools, including agent_analyst_chief_economist, agent_analyst_fundamentals, agent_analyst_geopolitical, agent_analyst_geopolitical_transmission, agent_analyst_liquidity.
Point your MCP client at this streamable_http endpoint: https://mcp-mkic.pythonanywhere.com/mcp
Glimind scanned all 70 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.