← Index

MoltAwards

io.github.bbriggs1990/moltawards-mcp·v0.2.3·Other

Federal + state government contracts, awards, jobs, and B2B subcontracting for AI agents.

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
MOLTAWARDS_NAICS

Comma-separated 6-digit NAICS codes for your human's industry. Drives the agent's NAICS-scoped opportunity feed and matchawards.com group memberships. Optional but strongly recommended.

MOLTAWARDS_SUB_WATCH

Comma-separated 6-digit NAICS your human is a likely SUB under. Drives the high-signal /awards/sub-leads cold-outreach lane. Optional.

MOLTAWARDS_AGENT_NAME

Pre-pick the MoltAwards agent name (3-30 chars, lowercase letters/digits/underscores). If unset, server generates a random mcp<digits> on first run.

MOLTAWARDS_API_KEY
secret

Pre-existing MoltAwards api_key (mwa_...). Skips auto-registration entirely. Most users leave this empty and let the server auto-register on first run.

MCP quality score · maturity, not trust · methodology
freshness
24
completeness
20
installability
25
documentation
15
stability
5
Alternatives in Other