Forge MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHAT_ID | No | Telegram chat ID. Required. Alias: FORGE_TELEGRAM_CHAT_ID. | |
| FORGE_DB | No | SQLite database path override. | |
| BOT_TOKEN | No | Telegram bot token. Required. Alias: FORGE_TELEGRAM_BOT_TOKEN. | |
| FORGE_PROOF_URL | No | Optional case link appended to SHORT pitches. | |
| FORGE_WALK_AWAY | No | Walk-away floor for offers. | |
| FORGE_DIGEST_PATH | No | Digest path override. | |
| FORGE_CONTRACT_ONLY | No | Set to 1 for strict contract/freelance HOT gate. | |
| FORGE_PAUSED_BOARDS | No | Manual board deprioritization list. | |
| FORGE_TELEGRAM_CHAT_ID | No | Alias for CHAT_ID. | |
| FORGE_TELEGRAM_BOT_TOKEN | No | Alias for BOT_TOKEN. |
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 |
|---|---|
| pause_weak_boardsB | Auto-pause boards with paid=0 and enough leads. |
| package_pricesC | Discovery / milestone / retainer from average won + anchor. |
| rate_adviceD | Your avg won vs listing budget mid. |
| check_red_flagsC | Red-flag checklist before you propose. |
| act_nowC | Priority queue of NEW leads (payability + age + rate). |
| queue_outreachC | Queue Merchant/MCP outreach draft → Telegram Send/Skip buttons. |
| list_outreachB | List pending outreach drafts. |
| capture_leadC | Track a job lead. Dedupes by URL and title fingerprint. |
| suggest_capabilitiesC | Rank your capability assets by relevance to a lead. |
| update_lead_statusC | Move a lead through the pipeline; wins feed learned magnets. |
| record_won_amountC | Record the agreed price once you win a lead. |
| record_paymentC | Record that you've actually been paid for a lead. |
| add_capabilityC | Add a reusable capability asset for future matching. |
| set_watchlistC | Set personal hunt keywords (money magnets). |
| pipeline_statusB | Show pipeline counts and win rate. |
| earnings_summaryB | Show total won, paid, and outstanding amounts. |
| platform_roiB | Show which job boards actually convert to paid work. |
| sla_statusC | SLA: burning NEW leads and proposed needing a 48h ping. |
| follow_upsD | Proposed leads silent too long — copy the EN ping. |
| scan_for_leadsB | Scan public job boards and auto-track capability matches. |
| hunt_jobsD | Hunt boards; push freelance-only HOT with RU brief + EN short pitch. |
| hot_leadsA | List fresh (status=new) leads waiting for your proposal. |
| chase_leadsC | NEW leads past SLA — propose these first. |
| brief_leadC | Explain a vacancy in clear Russian. |
| draft_proposalC | SHORT + FULL pitches with i18n opener, A/B variant, anchor price. |
| morning_digestC | Push top NEW with RU brief + SHORT EN (Telegram buttons). |
| evening_followupC | Evening: SLA + proposed pings + board pause advice. |
| board_adviceC | Deprioritize boards with paid=0 and enough leads. |
| log_win_reasonC | Win journal: one phrase why the client chose you. |
| win_journalC | Recent wins with amounts, pitch variant, and reasons. |
| pitch_ab_statsB | A/B win rates for short vs full pitches. |
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 31 tools
Several tool clusters overlap heavily: act_now/hot_leads/chase_leads all surface fresh NEW leads to act on, scan_for_leads/hunt_jobs both scan boards for leads, and pause_weak_boards/board_advice both deprioritize paid=0 boards. Descriptions hint at nuances (age, SLA, push vs track) but an agent could easily misselect within these pairs.
Casing is consistently snake_case, but the verb/noun pattern is mixed: some tools are verb_noun (capture_lead, record_payment, draft_proposal) while many others are bare noun phrases (pipeline_status, hot_leads, follow_ups, win_journal, rate_advice). Readable but not a predictable convention.
31 tools is heavy for a lead-hunting/pipeline server, and the count is inflated by overlapping capabilities (multiple lead-surfacing, board-advice, and outreach tools) rather than distinct operations. Bloat suggests several tools could be merged or parameterized.
The lifecycle is well covered: capture/scan leads, qualify (red flags, pricing, rate advice), outreach/proposals, pipeline status, payments, board ROI, and win analytics. Only minor gaps (e.g., no explicit lead delete/archive or contact management) that agents can work around.