# How to Test MCP Server Behavior | Reelier

Record real MCP calls, compile the observed workflow, and replay declared checks against observed outcomes. This tests selected behavior beyond a static schema, but only for recorded calls and declared checks. Schema compatibility, unrecorded branches, and complete behavioral coverage remain separate questions.

Evidence state: explained against released `reelier@0.32.0` on 2026-08-12.

## Evidence note

The linked guide and recording reference document the record, compile, and replay workflow. This cluster retains no claim of total behavioral coverage.

## Record representative calls

Start with tool calls that exercise the behavior you care about. The resulting workflow covers those observed calls, not unrecorded server branches.

## Declare checks

Compilation turns observed calls into a fixed workflow. Assertions name the response conditions that replay should enforce; an undeclared property is not silently checked.

## Replay against the server

Replay re-executes the fixed calls and evaluates the declared checks against observed outcomes. This complements schema validation but does not replace it.

## Non-claims

This does not prove that an action was safe or semantically correct.

This does not prove that every write was observed or receipted.


## Falsifier

A materially changed recorded tool outcome that is covered by a declared check but cannot be observed by replay would falsify this claim for that case.

## Sources

- [Released compiler implementation](https://unpkg.com/reelier@0.32.0/dist/compile.js)
- [Released runner contract](https://unpkg.com/reelier@0.32.0/dist/runner.d.ts)
- [Test MCP servers guide](https://www.reelier.com/guides/test-mcp-servers)
- [MCP recording reference](https://www.reelier.com/learn/mcp-recording)

## Citation-friendly definition

A recorded MCP workflow tests selected calls by replaying them and evaluating declared checks; unrecorded branches and undeclared behavior remain outside its coverage.

## Related evidence

- [What an agent receipt actually proves](https://www.reelier.com/evidence/what-agent-receipt-proves)
- [Record MCP tool calls](https://www.reelier.com/evidence/record-mcp-tool-calls)

Canonical: https://www.reelier.com/evidence/test-mcp-server-behavior

Markdown twin: https://www.reelier.com/evidence/test-mcp-server-behavior/md