agent-exporter is a local archive and governance workbench for AI agent transcripts. It exports transcript data to browsable HTML receipts and publishes an archive shell for organizing transcripts, reports, and integration evidence in a local workspace.
From the registry: Local stdio MCP bridge for archive publishing, retrieval, and governance evidence.
Please install the `agent-exporter-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Rust and Cargo** — The README uses `cargo run` as the primary way to launch the local stdio bridge, so Rust/Cargo must be installed.
- **Install Codex CLI / app-server capability** — By default, the tool launches `codex app-server` for the canonical source path. This must be available on PATH unless you override it with custom app-server command arguments.
Optional prerequisites:
- Set CODEX_HOME if using local Codex archival source — Only needed for `--source local` when the local Codex ledger is not in the default location. Resolution order is `--codex-home`, then `CODEX_HOME`, then `~/.codex`.
Canonical MCP server config (stdio transport):
- command: `cargo`
- args: ["run","--"]
- optional environment variables:
- `CODEX_HOME`: Path to the local Codex home directory when using `--source local` and not supplying `--codex-home`. (example: `<your-codex-home-path>`)
Note: The README identifies a local stdio MCP bridge, but does not provide a full MCP invocation command in the README itself beyond pointing to `llms-install.md` and `server.json`. The simplest documented launch shape in this README is running the project locally via `cargo run --`. Default behavior launches `codex app-server` internally. No HTTP/SSE endpoint is documented here.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.