About earnings-watch
Earnings Watch tracks verified issuer earnings dates and results documents through a CLI, Python API, and MCP server. It combines model-proposed dates with deterministic checks for quoted evidence and consistent issuer, period, and timing; calendar changes are planned for a client to apply externally.
Key features
- 01Verified earnings dates and documents
- 02Evidence, revisions, and history
- 03Issuer watchlists and status
- 04Optional calendar operation plans
- 05CLI, Python API, and MCP tools
Use cases
- 01Checking upcoming issuer earnings dates
- 02Reviewing evidence and revised event history
- 03Planning calendar updates from verified events
MCP support
The MCP server exposes tools for upcoming dates, events, documents, changes, watchlists, calendar planning, and status, plus prompts and an upcoming-calendar resource. Calendar plans are applied by the MCP client through its external Outlook app, then acknowledged.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
10Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| days | integer | No | |
| limit | integer | No | |
| scope | string | No | |
| types | any | No | |
| cursor | any | No | |
| tickers | any | No |
Details
From the project READMEEarnings Watch
Verified issuer earnings calendars and results documents through a CLI, Python API and MCP server. Models propose dates; deterministic checks require quoted evidence and consistent issuer, period and timing. A call time never silently becomes a publication time.
Calendar updates are optional. Earnings Watch produces an operation plan; your MCP client uses its external Outlook app to apply it and acknowledges confirmed writes. No Microsoft credentials or calendar SDK are required by this package.
Maintained source and contributions: benjamin-di/earnings-watch. See Source and releases.
Requires Python 3.12+. Install the published package with uv tool install earnings-watch, or develop from a source checkout:
make bootstrap
uv run earnings-watch init
uv run earnings-watch doctor
uv run earnings-watch sources import examples/sources.yaml
uv run earnings-watch watch EXAMPLE
uv run earnings-watch upcoming --format json
The example uses reserved domains and fictional data; replace its source URLs and issuer metadata before fetching. There is no bundled issuer universe or market-data subscription.
Maintenance and models
Serving reads SQLite and updates personal follows/ledgers; it never fetches issuer pages or calls a model. Run maintenance separately:
uv run earnings-watch sweep --dry-run
uv run earnings-watch sweep
uv run earnings-watch sweep --docs-only
uv run earnings-watch worker
The default backend is none: it preserves existing dates and still polls official release providers. To extract new dates, install and sign into your own Claude Code or Codex CLI, then configure it in earnings-watch.toml:
[llm]
backends = ["claude-code", "codex", "none"]
max_calls_per_run = 20
Supported minimum versions are Claude Code 2.1.312 and Codex 0.164.0. Run earnings-watch doctor --live to check capabilities and an optional model canary. The package has no login flow. Model usage follows your CLI account's limits and terms. Only an explicit sign-in or account-limit refusal, or a configured Codex endpoint that is unreachable or failing before any output, tries the next backend; a timed-out run is not repeated in the same tick.
Codex runs with --ignore-user-config. To send it through an OpenAI Responses-compatible endpoint, set both codex_base_url and codex_key_env (the name of the environment variable holding its key) under [llm]; the key itself never goes in the file. Use https:// for any endpoint that is not on the local host. Claude Code receives ANTHROPIC_BASE_URL and CLAUDE_CODE_MAX_RETRIES from the environment, so a bounded retry count lets an unavailable endpoint fail before the task timeout.
MCP
A local client configuration, after initialization:
{"mcpServers":{"earnings":{"command":"earnings-watch","args":["serve","--stdio"]}}}
| Tool | Purpose |
|---|---|
earnings_upcoming | Bounded upcoming dates with timing uncertainty |
earnings_get_events | Evidence, revisions and recent history |
earnings_documents | Official result-document links and verification status |
earnings_changes | Cursor-based public change feed |
earnings_watchlist | Your follows and registration states |
earnings_watch | Follow an issuer; queue registration or resolve ambiguity |
earnings_unwatch | Remove a manual follow |
earnings_calendar_plan | Plan optional external calendar operations |
earnings_calendar_ack | Record confirmed operations from a signed plan |
earnings_status | Catalogue and maintenance status |
Prompts: earnings_briefing, results_brief, sync_to_my_outlook. Resource: earnings://upcoming.ics. Exact times require verified clock and timezone evidence; otherwise calendar entries are all-day. Outlook operations never include attendees.
HTTP standalone mode uses a separate bearer token per person at /users/<id>/mcp. Gateway mode accepts a configured backend bearer and an immutable subject header from the admission gateway at /mcp. These modes are separate trust boundaries; see permissions.
Connections page and notifications
The optional Connections page provides Upcoming, Your companies, Notifications and Calendar in one place. Sign in, add companies or preview a holdings import, then subscribe to your private calendar feed. Facts are shared; holdings, watchlists, mutes, preferences and receipts are personal.
Results-out notifications are enabled for new people. Daily briefs and urgent changes are optional. Mail submission requires a separately configured transport; the server and acquisition worker never send messages themselves.
Docker Compose
cp earnings-watch.example.toml earnings-watch.toml
docker compose build
docker compose run --rm server init
docker compose run --rm server users add example
docker compose up -d
Save the returned token privately and use it only on that person's HTTP path. The server binds to loopback by default. Both images run as uid 1000; Compose drops capabilities, prevents privilege escalation and mounts the root filesystem read-only. The worker image includes pinned model CLIs; their auth volume is optional with backends=["none"]. Configure CLI sign-in outside the read-only worker before enabling model maintenance. Protect auth files and the data volume from other users.
Use --config PATH, --person ID, and --json with the CLI. Settings come from TOML and EARNINGS_WATCH_* environment variables. See operations, architecture, providers and design decisions.
Development
make check verifies lock drift, lint, formatting, types, dependency boundaries, offline tests and wheel/source builds. Tests use synthetic issuers and fake network/model/account boundaries. Real-model and real-page checks are separate operator gates. Read CONTRIBUTING.md and SECURITY.md.
See implementation status for completed capabilities, release gates and the production adapter work still required before cutover.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.