Skip to content

OnFire MCP Plugin

The OnFire MCP Plugin is a Claude Code plugin that ships a curated set of OnFire skills. A skill is a high-level recipe — orchestration, rendering contract, and behavioural rules — built on top of one or more OnFire MCP tools. The MCP server owns the data; the plugin owns how an agent should use that data well.

The plugin contributes ten skills, grouped by what the user is trying to do:

SkillWhat it does
onfire-prospectingOrchestrator for the five atomic prospecting skills. Routes work end-to-end.
ai-prospectingAtomic: run AI prospecting or score one named person.
match-companyAtomic: resolve a company to a verified LinkedIn identity.
match-personAtomic: resolve a person to a verified LinkedIn profile.
contact-data-enrichmentAtomic: append verified emails / phones. Enforces the two-phase consent flow.
manage-ai-prospectingAtomic: shadow lifecycle for the prospecting schema (draft, test, ship, discard).
bdr-account-researchGenerate the customer-facing BDR account research HTML report.
account-expansion-planGenerate a single-account Expansion Opportunities Plan (CRM + prospecting + signals).
poc-intelligenceGenerate a tenant-wide POC Intelligence Report (funnel + plays + playbook).
prospect-signals-botA Slack-channel watcher that posts a minimal new-business signal summary per request.

The MCP server is stateless and policy-light by design — it exposes typed tools, scopes them to the authenticated tenant, and returns structured JSON. That’s the right shape for any agent runtime to consume.

The plugin layers on top:

  • Orchestration. Which tool to call first when you only have a name. When to poll vs. retry. Which dataset to hand off to which next tool.
  • Rendering contracts. A BDR brief / expansion plan / POC report are HTML deliverables with strict layout and branding rules. The plugin enforces those rules so the agent produces a consistent artifact each time.
  • Behavioural rules. Required user-approval phrases for paid tools. How to surface the download_url from download_dataset. How to re-format reasoning sentinels for the user.

In short: the MCP server is for any agent; the plugin is for agents that need to produce OnFire-shaped deliverables without rediscovering the rules every time.

SkillPrimary MCP tools
onfire-prospectingmatch_company, match_person, ai_prospecting, contact_data_enrichment, manage_ai_prospecting, query_datasets, describe_dataset, download_dataset, list_datasets
ai-prospectingai_prospecting, ai_prospecting_field_glossary, dataset companions
match-companymatch_company
match-personmatch_person
contact-data-enrichmentcontact_data_enrichment
manage-ai-prospectingmanage_ai_prospecting, ai_prospecting (shadow runs)
bdr-account-researchbdr_account_research, query_datasets, the typed follow-up tools
account-expansion-planget_tenant_settings, query_intent_signals, ai_prospecting — plus the CRM integration proxy outside this tool list
poc-intelligenceget_tenant_settings, list_datasets, query_datasets, describe_dataset, search_people, ai_prospecting — plus the CRM integration proxy, Metabase, and Snowflake outside this tool list
prospect-signals-botquery_intent_signals — plus Slack outside the MCP

The plugin is distributed as a .plugin file. Drop it into Claude Code the same way you install any other plugin and the skills become available immediately. The plugin assumes you’ve already connected the OnFire MCP server — there are no extra credentials to manage.