recon_match
Parses a camt.053.001 statement (same schema-subset checks as camt053_parse) and a counterpart expectation set (CSV, header EndToEndId,Amount,Currency,Date -- same strict RFC 4180 parser as the WORKBOOK-1 CSV tools), then runs the SAME deterministic match engine as the tools/565 browser workbench...
This record as markdown: /tools/postoaklabs-ainumbers-mcp-apps/recon-match.md
What recon_match does on Ainumbers Mcp Apps
AI agents call recon_match to retrieve information from Ainumbers Mcp Apps without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
statement_xml | string | Yes | camt.053.001 XML statement document text. |
amount_tolerance | number | — | Absolute amount-match tolerance (default 0.01). |
expectations_csv | string | Yes | Counterpart expectations, CSV with header EndToEndId,Amount,Currency,Date. |
date_tolerance_days | number | — | Date-match tolerance in days (default 0). |
Parameters from the server's own tool schema.
Why recon_match is rated Low
The tool parses input data (a camt.053 statement and a CSV expectation set), runs a deterministic matching engine, and returns reconciliation results. It performs no writes, executes no external commands, and has no financial transaction capability. The server explicitly states 'Read-only, no auth, zero PII', confirming the tool only computes and returns data.
From the tool's definition Read-only, no auth, zero PII (server description); Returns matches, exceptions, and a reconciliation receipt — purely analytical output with no side effects
Attacks that exploit this kind of access
The rule that runs recon_match safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ainumbers Mcp Apps, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For recon_match, this is the rule to start with:
recon_match is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ainumbers Mcp Apps, apply this rule, and every recon_match call is checked against it from then on.
Questions about recon_match
Parses a camt.053.001 statement (same schema-subset checks as camt053_parse) and a counterpart expectation set (CSV, header EndToEndId,Amount,Currency,Date -- same strict RFC 4180 parser as the WORKBOOK-1 CSV tools), then runs the SAME deterministic match engine as the tools/565 browser workbench: EndToEndId exact match first (statement order), then amount+date tolerance + currency match (first unmatched expectation in CSV order). Returns matches, exceptions (unmatched entries/expectations), and a reconciliation receipt (statement digest, expectation-set digest, match-rule declaration, counts, exception digests, execution_hash) -- byte-identical to the browser tool for the same inputs. Prepare/hash/receipt only; per-exception disposition receipts are the browser workbench's interactive follow-on. It is categorised as a Read tool in the Ainumbers Mcp Apps MCP Server, which means it retrieves data without modifying state.
recon_match accepts 4 parameters: statement_xml, amount_tolerance, expectations_csv, date_tolerance_days. Required: statement_xml, expectations_csv. The full parameter table on this page comes from the server's own tool schema.
Register the Ainumbers Mcp Apps MCP server in PolicyLayer and add a rule for recon_match: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ainumbers Mcp Apps. Nothing to install.
recon_match is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the recon_match rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for recon_match. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
recon_match is provided by the Ainumbers Mcp Apps MCP server (postoaklabs/ainumbers-mcp-apps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ainumbers Mcp Apps, and thousands of servers like it.
This server
Across the catalogue