Evaluate a proposed agent spend against a policy, returning ELIGIBLE, DENY, or STEP_UP with stable reason codes. Serves as local policy evidence, not payment authorization.
MIT
460,228 tools. Updated 2026-08-18 02:42
"Spond" matching MCP tools:
- Read a past session as a chronological transcript to review, analyze, or summarize its content. Includes user/assistant text and references, with options to page through messages and open subagent sessions.Apache 2.0
- Run read-only SQL over sessions, messages, and parts to aggregate data, find exact strings, analyze tool calls, or export as parquet/NDJSON.Apache 2.0
- Retrieve relevant messages from past agent sessions by semantic or exact-word search. Filter results by project, date, session, or source agent to find what was discussed.Apache 2.0
- Retrieve a message with its full part bodies (tool calls, results, reasoning, files) and nearby messages for context. Pass a message ID; set context_before/after to adjust the window.Apache 2.0
- Analyze API usage costs by capability and provider, showing total spend, execution counts, and cost averages for specified periods.MIT
Matching MCP Servers
- Flicense-qualityDmaintenanceEnables fetching upcoming events for London Desperados CC from Spond via a single tool, get_desperados_events.
- Alicense-qualityDmaintenanceAn MCP server for managing kids' sports activities on Spond. Built for parents who want to give AI assistants access to upcoming matches, training schedules, and attendance.5MIT
Matching MCP Connectors
Federal contract intelligence: $7T+ awards, SAM.gov opps, pWin verdicts, recompetes, protests.
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
- Calculate carbon emissions from travel spending by inputting spend type, amount, currency, location, and year to assess environmental impact.MIT
- Generate step-by-step cancellation instructions for any subscription service, guiding users to disable autopay on PhonePe, GPay, or Paytm.
- Calculate total monthly and annual subscription spend, identify savings from unused services, and detect price increases.
- Analyze recent non-billing emails from a service to identify whether a subscription has high engagement or no engagement.
- Get recent verified spend activity signals from the Crinkl network. Each signal represents a cryptographically attested receipt that has passed OCR extraction, store resolution, and hard verification. Signals include store name, category (e.g. Grocery & Supermarkets, Gas & Convenience), CBSA metro code, and spend amount — but no personally identifiable information. Use resolve-cbsa to convert CBSA codes to metro area names.Connector
- Get your QuoteFirst spend this month in cents, total and broken down by model.Connector
- Which apps/agents can pull funds from this Base wallet? — Base Account spend permissions let an app or agent spend a scoped, recurring allowance from a wallet — the primitive behind autonomous agent payments on Base. This reconstructs a wallet's ACTIVE spend permissions from onchain approve/revoke events and flags the dangerous ones: unlimited allowance, no expiry, unrecognized spender. The Base-native, agent-era drain check that ERC-20 approval tools can't see. Required input: wallet. Priced $0.05 per call over x402 on Base; send a prepaid x-credit-token header for unlimited calls, or get 1 free call/day per tool. No wallet or API key required.Connector
- Get the geographic and category distribution of verified spends over a trailing window. Returns a breakdown by store category and CBSA (Core Based Statistical Area) metro code, enabling analysis of where and how verified commerce is distributed across the United States.Connector