Catalyst Edge MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CATALYST_EDGE_HOST | No | Host for streamable HTTP. Loopback addresses only. Defaults to 127.0.0.1. | 127.0.0.1 |
| CATALYST_EDGE_PORT | No | Port for streamable HTTP. Defaults to 8000. | 8000 |
| CATALYST_EDGE_GDELT | No | Enable GDELT Web NGrams discovery. Defaults to disabled. When enabled, request reads are cache-only and refresh is out of band. | disabled |
| CATALYST_EDGE_BLUESKY | No | Enable Bluesky partial public attention. Defaults to disabled. Dev needs no request-time network call. | disabled |
| CATALYST_EDGE_TRANSPORT | No | Transport for the MCP server. Accepts stdio or streamable-http. Defaults to stdio. | stdio |
| CATALYST_EDGE_ISSUER_FEEDS | No | Enable issuer feeds. Defaults to disabled. Explicit opt-in only after source-specific rights and output review. | disabled |
| CATALYST_EDGE_REGISTRY_PATH | No | Optional local JSON registry replacing the complete reviewed registry. Defaults to packaged reviewed_registries.json. | packaged reviewed_registries.json |
| CATALYST_EDGE_EVIDENCE_STORE | No | Path to the local SQLite/WAL evidence store. Defaults to ~/.local/state/catalyst-edge-mcp/evidence.sqlite3. | ~/.local/state/catalyst-edge-mcp/evidence.sqlite3 |
| CATALYST_EDGE_SEC_USER_AGENT | Yes | User agent string for SEC EDGAR. Required for live data collection; missing identity blocks live collection. | |
| CATALYST_EDGE_SENTIMENT_MODEL | No | Sentiment model selection. Defaults to disabled. Any other value fails configuration until a reviewed candidate passes every gate. | disabled |
| CATALYST_EDGE_OPTIONS_PROVIDER | No | Options provider selection. Accepts none, auto, flowalgo, cheddarflow, yfinance. Defaults to none. yfinance is private diagnostic only. | none |
| CATALYST_EDGE_GDELT_LOOKBACK_DAYS | No | Event-store reporting window used by each GDELT background refresh. Defaults to 14 (1-90). | 14 |
| CATALYST_EDGE_GDELT_MAX_AGE_SECONDS | No | Last-success age after which request-time cache health becomes stale. Defaults to 900; must be at least the refresh interval. | 900 |
| CATALYST_EDGE_GDELT_REFRESH_SECONDS | No | Period between bounded background GDELT attempts. Defaults to 300 (60-86400). | 300 |
| CATALYST_EDGE_BLUESKY_MAX_AGE_SECONDS | No | Fail-closed maximum age since the last Bluesky collector check. Defaults to 43200. | 43200 |
| CATALYST_EDGE_BLUESKY_REFRESH_SECONDS | No | Out-of-band completed-day refresh cadence for Bluesky. Defaults to 21600 (six hours). | 21600 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| catalyst_edge_scoreB | Use for ticker research to assess recent evidence, provenance, and next checks. |
| catalyst_edge_claim_sourcesA | Use with a dossier claim ID to read one bounded page of its immutable source records. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
Each tool targets a distinct function: one for generating/assessing research scores on a ticker, the other for retrieving source records for a specific claim ID. No overlap in purpose or inputs.
Both tools share the 'catalyst_edge_' prefix and use snake_case with a clear noun structure. The pattern is consistent and predictable, making it easy to infer each tool's role.
With only two tools, the server has a minimal but plausible scope. While each tool clearly serves a distinct purpose, the very low number makes the set feel thin and raises expectations for more coverage.
The two tools cover a core research workflow (get score, then read claim sources), but the server lacks other potentially useful operations such as listing dossiers or searching claims. Given the apparent narrow domain, the surface is reasonably complete for a read-only assistant, though a bit minimal.