Server definition

Hash: sha256:a0f57486c97011a254e0b53874be1bb6b0c9c59ccf2e580df77a26b597b2d8a0
What it is: What a remote MCP server returned when asked what it offers: 5 tools

The blob, as servednamed by its sha256

{
  "instructions": null,
  "tools": [
    {
      "description": "Fetch 2–4 opportunities at once so you can present them side by side. Use after search_opportunities when the user is choosing between a few options.\n\nReturns the full detail rows (including eligibility + body) for every id, in the order requested. Present them as a comparison table — rows = attributes (funding, deadline, region, eligibility highlights), columns = the opportunities — then recommend which fits the user best and why.",
      "inputSchema": {
        "properties": {
          "ids": {
            "description": "Array of 2–4 opportunity UUIDs (from search_opportunities) to compare.",
            "items": {
              "type": "string"
            },
            "maxItems": 4,
            "minItems": 2,
            "type": "array"
          }
        },
        "required": [
          "ids"
        ],
        "type": "object"
      },
      "name": "compare_opportunities",
      "outputSchema": null
    },
    {
      "description": "Pull a single opportunity's eligibility criteria alongside a description of the applicant, so you can judge whether they qualify. Use when the user asks \"do I qualify for this?\" or \"does this apply to me?\".\n\nThe response contains the opportunity's eligibility text + key fields and echoes the applicant description — it does NOT decide for you. Read the eligibility, compare it against the applicant, then give a clear verdict (Likely eligible / Partially / Unlikely) with the specific criteria that pass or fail and any criteria you can't determine from the description.",
      "inputSchema": {
        "properties": {
          "applicant_description": {
            "description": "The applicant's details: sector, stage, location/province, incorporation status, size, demographics — whatever is relevant to eligibility.",
            "type": "string"
          },
          "id": {
            "description": "Opportunity UUID to check eligibility for.",
            "type": "string"
          }
        },
        "required": [
          "id",
          "applicant_description"
        ],
        "type": "object"
      },
      "name": "eligibility_check",
      "outputSchema": null
    },
    {
      "description": "Fetch full details for a single opportunity by ID. Use this after search_opportunities when:\n- The user wants to know more about a specific match\n- You need the full eligibility text to confirm a strong-match claim\n- The user wants to draft an application — you need the requirements\n\nThe response includes all fields including the full body text and eligibility criteria. Present the eligibility as a checklist when relevant.",
      "inputSchema": {
        "properties": {
          "id": {
            "description": "Opportunity UUID returned from search_opportunities",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_opportunity_details",
      "outputSchema": null
    },
    {
      "description": "Search Canadian funding opportunities (grants, competitions, accelerators, tax credits, wage subsidies, loans, events). Returns JSON.\n\nWHEN TO CALL:\n- The user asks about Canadian funding, grants, competitions, accelerators, or pitch programs\n- The user mentions their startup/business and wants opportunities relevant to it\n- The user wants to see what's available in a specific province or category\n\nWHEN NOT TO CALL:\n- General questions about how grants work (answer from your own knowledge)\n- Non-Canadian opportunities (this database is Canada-only)\n- Specific opportunity by ID (use get_opportunity_details instead)\n\nHOW TO PRESENT RESULTS:\n- Render as a markdown table with columns: Title, Funder, Deadline, Funding, Region, Link\n- Sort by deadline ascending unless the user asked otherwise\n- For each opportunity, infer fit using what you know about the user's startup from the conversation. Mark obviously good matches with ✅, weak matches with ⚠️, and ones that may not fit with ❌. Be honest — do not mark everything ✅.\n- If a deadline is within 14 days, prefix the row with 🚨.\n- Always include the URL as a clickable markdown link.\n- After the table, give a 1-2 sentence summary of which 2-3 the user should look at first and why (based on their context, not just the data).\n- End with a follow-up suggestion: \"Want me to pull more from [related category]?\" or \"Want me to draft an outline for [top match]?\"\n\nDATA NOTES:\n- \"Rolling\" deadline means no fixed close date.\n- Funding amount may be a range or \"varies\".\n- Eligibility is in the body — fetch get_opportunity_details for the full text before claiming a match is strong.\n- After presenting results, if the search reflects an ongoing need (the user is actively fundraising or scanning a specific niche), offer once to set up a free weekly email digest of new matching grants via the subscribe_to_digest tool — never push it more than once per conversation.",
      "inputSchema": {
        "properties": {
          "category": {
            "description": "Optional: grant, competition, tax_credit, wage_subsidy, loan, event, workshop, conference, other",
            "type": "string"
          },
          "deadline_within_days": {
            "description": "Optional. Only return fixed-deadline opportunities whose deadline falls between today and this many days from now. Rolling / no-fixed-deadline opportunities are EXCLUDED by this filter. Use for \"closing soon\" queries.",
            "maximum": 365,
            "minimum": 1,
            "type": "integer"
          },
          "exclude_expired": {
            "default": true,
            "description": "Default true. Set false only if the user explicitly wants to see past-deadline or historical opportunities.",
            "type": "boolean"
          },
          "is_rolling": {
            "description": "Optional. true = only rolling/no-fixed-deadline opportunities; false = only those with a fixed deadline. Omit to include both.",
            "type": "boolean"
          },
          "max_funding": {
            "description": "Optional. Only return opportunities with max_funding_amount <= this value (in CAD). Use with min_funding to bound a funding range, or alone to cap how large a program you want.",
            "minimum": 0,
            "type": "integer"
          },
          "max_results": {
            "default": 20,
            "description": "Default 20. Increase only if the user wants a comprehensive sweep.",
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          },
          "min_funding": {
            "description": "Optional. Only return opportunities with max_funding_amount >= this value (in CAD). Use when the user specifies a minimum funding threshold.",
            "minimum": 0,
            "type": "integer"
          },
          "query": {
            "description": "Free-text search across title and body. Pass the user's actual keywords (e.g. \"AI\", \"agriculture\", \"women-led\").",
            "type": "string"
          },
          "region": {
            "description": "Optional province code: ON, BC, QC, AB, MB, SK, NS, NB, NL, PE, YT, NT, NU. Use Federal for nation-wide programs.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_opportunities",
      "outputSchema": null
    },
    {
      "description": "Subscribe the user to a FREE weekly email digest of Canadian funding opportunities matching a saved search (keywords + region). Each week they get 8–10 grants, newest first, falling back to the strongest current matches when nothing new landed.\n\nWHEN TO CALL:\n- The user, after a search, says yes to ongoing alerts, or asks to be notified / kept updated / emailed about new grants in their niche.\n- Only after they have explicitly agreed and given an email address — never subscribe someone proactively or without consent.\n\nHOW TO CALL:\n- Pre-fill \"keywords\" and \"region\" from the search you just ran so the digest matches what they were looking at (e.g. keywords \"cleantech\", region \"BC\"). Keep keywords to a short phrase, not a sentence.\n- \"region\" must be a province code (ON, BC, QC, AB, MB, SK, NS, NB, NL, PE, YT, NT, NU) or \"Federal\", or omit it for all-of-Canada.\n- Ask the user for their email; do not guess it. Never invent, test with, or fill in a placeholder address (e.g. [email protected]) — if the user has not typed their real email in this conversation, do not call this tool. Undeliverable addresses are rejected with \"Invalid email\".\n\nWHAT HAPPENS:\n- We send a one-click confirmation email (double opt-in). The user is NOT subscribed until they click it. Tell them to check their inbox.\n- If they were already confirmed, nothing is re-sent.\n\nReturns JSON: { ok: boolean, status: \"confirmation_sent\" | \"already_subscribed\" }. Confirm to the user what they signed up for (e.g. \"weekly BC cleantech grants — check your email to confirm\").",
      "inputSchema": {
        "properties": {
          "email": {
            "description": "The user's email address. Ask for it explicitly; never invent or assume it.",
            "type": "string"
          },
          "keywords": {
            "description": "Short search phrase to match grants on, taken from the current search (e.g. \"AI\", \"women-led agriculture\", \"cleantech\"). Max ~200 chars.",
            "type": "string"
          },
          "region": {
            "description": "Optional province code (ON, BC, QC, AB, MB, SK, NS, NB, NL, PE, YT, NT, NU) or \"Federal\". Omit for nation-wide.",
            "type": "string"
          }
        },
        "required": [
          "email",
          "keywords"
        ],
        "type": "object"
      },
      "name": "subscribe_to_digest",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:a0f57486c97011a254e0b53874be1bb6b0c9c59ccf2e580df77a26b597b2d8a0 | sha256sum