Skip to main content
Glama

PitchSpark: Pre-Seed & Seed Startup Pitches

Investors: ask a startup founder for an intro through PitchSpark

pitchspark_request_intro_v1

For investors: send the founders of one startup on PitchSpark a request to connect, with a short message, through PitchSpark's own in-app contact flow. Use when: an investor has read a pitch (from pitchspark_search_pitches_v1 or pitchspark_get_pitch_v1) and has asked for an introduction to its founders. Every request is sent in the investor's name, from their account. Do not use for: getting founder contact details (never returned, by this or any tool); founders contacting investors or other founders (contact is investor-initiated only); bulk or unsolicited outreach the investor has not asked for; saving a pitch for later (use pitchspark_watch_pitch_v1). Requires a PitchSpark API key (psk_...) from an investor account (self-declared; PitchSpark does not verify accreditation), sent as "Authorization: Bearer psk_..." or in the X-API-Key header; calls without a key, with a submit token (pss_...) or with a key from a non-investor account return UNAUTHORIZED. PitchSpark does not verify investors or founders, does not recommend investments and takes no part in any resulting deal. PitchSpark notifies the founder in the app (and by email) and the founder replies inside PitchSpark, in the investor's Mailbox. The reply never comes back through this tool, and no email address, phone number, website, social profile or calendar link of the founder is ever returned. The message reaches the founders as the investor's own words, after the line "Sent via this investor's AI assistant (PitchSpark MCP)."; email addresses (also spelled out), phone numbers, links, IP addresses and @handles are removed (replaced with [email], [phone], [link], [handle]) and it is cut to 1000 characters. Returns {"status","intro_id","next_steps"}: status "requested" (sent), "already_requested" (the investor already has a conversation with these founders; nothing new is sent; follow-ups happen in the PitchSpark Mailbox) or "quota_exhausted" (a free account has used its 3 new founder conversations this calendar month; nothing is sent, intro_id is null; Pro is unlimited). Each new conversation counts against the account's monthly allowance, shared with Contact Founder on pitchspark.io. An id that does not exist, a pitch that is not public, and a pitch whose founders have opted out of AI agents all answer NOT_FOUND; a pitch the investor owns or is on the team of is INVALID_ARGUMENT. Limits: 5 calls per API key and 5 per account per UTC day (RATE_LIMITED with retry_after_seconds after that), and 30 tool calls per minute per connection. Calls are logged without the message text. Errors are JSON {"error":{"code","message","retry_after_seconds"}}: UNAUTHORIZED, INVALID_ARGUMENT, NOT_FOUND, RATE_LIMITED, INTERNAL.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pitch_id": "<pitch_id>",
      "message": "<message>"
    },
    "name": "pitchspark_request_intro_v1"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageYesThe investor's note to the founders, in the investor's words: who they are and why they are interested, e.g. "Hi, I lead seed deals in clinic software at a small fund and would love to hear how the pilots are going." Up to 1000 characters are kept. Email addresses, phone numbers, links and @handles are removed before the founder sees it.
pitch_idYesThe pitch id, copied exactly from the "id" field of a search or details result: 1 to 64 letters, digits, "_" or "-". Ids are not derived from company names; an id that does not exist answers NOT_FOUND.

Output Schema

NameRequiredDescriptionDefault
errorNoPresent only when the call failed (isError true).
statusNo
intro_idNo
next_stepsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "anyOf": [
      +    {
      +      "required": [
      +        "status",
      +        "intro_id",
      +        "next_steps"
      +      ]
      +    },
      +    {
      +      "required": [
      +        "error"
      +      ]
      +    }
      +  ],
      +  "properties": {
      +    "error": {
      +      "additionalProperties": false,
      +      "description": "Present only when the call failed (isError true).",
      +      "properties": {
      +        "category": {
      +          "description": "The error class.",
      +          "enum": [
      +            "RATE_LIMITED",
      +            "QUOTA_EXCEEDED",
      +            "UNAUTHORIZED",
      +            "FORBIDDEN",
      +            "VALIDATION_ERROR",
      +            "NOT_FOUND",
      +            "CONFLICT",
      +            "UNKNOWN_TOOL",
      +            "INTERNAL"
      +          ],
      +          "type": "string"
      +        },
      +        "code": {
      +          "description": "Machine-readable error code, e.g. RATE_LIMITED, UNAUTHORIZED, FORBIDDEN, INVALID_ARGUMENT, NOT_FOUND, CONFLICT, PITCH_LIMIT_REACHED, INTERNAL.",
      +          "type": "string"
      +        },
      +        "message": {
      +          "description": "A short human-readable explanation, safe to show the user. Never a stack trace.",
      +          "type": "string"
      +        },
      +        "retry_after_seconds": {
      +          "description": "Seconds to wait before retrying, when waiting helps.",
      +          "minimum": 0,
      +          "type": "integer"
      +        },
      +        "retryable": {
      +          "description": "true when the same call can succeed later without changes.",
      +          "type": "boolean"
      +        }
      +      },
      +      "required": [
      +        "code",
      +        "message"
      +      ],
      +      "type": "object"
      +    },
      +    "intro_id": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "next_steps": {
      +      "type": "string"
      +    },
      +    "status": {
      +      "enum": [
      +        "requested",
      +        "already_requested",
      +        "quota_exhausted"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes far beyond the annotations: discloses redaction of emails/phones/links/handles, the 1000-character truncation, the appended AI-assistant line, quota mechanics (3 free conversations/month, shared with Contact Founder), per-key/per-account daily limits with retry_after_seconds, and log handling. It also enumerates the return statuses and error codes, which the annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded and organized into clear blocks (use when, do not use, auth, returns, limits, errors), which is appropriate for a tool with this many operational rules. It is nonetheless very long and repeats the no-contact-details guarantee twice ('never returned, by this or any tool' and the later list of email/phone/website/social/calendar).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers everything an agent needs for a state-changing, open-world call: auth requirements, failure modes, quota and rate limits, what the founder receives, and what the reply path is (Mailbox, never through this tool). The output schema exists, yet the description still usefully explains the three status values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already defines both fields well; the description adds contextual meaning the schema lacks, such as where pitch_id comes from in practice and that owning/being on the team of the pitch yields INVALID_ARGUMENT. It largely restates the schema's redaction rules for message, so not a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('send the founders of one startup ... a request to connect, with a short message') and immediately distinguishes itself from pitchspark_search_pitches_v1, pitchspark_get_pitch_v1 and pitchspark_watch_pitch_v1. An agent can tell exactly what this does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Has explicit 'Use when' (investor has read a pitch and asked for an intro) and 'Do not use for' clauses covering contact-detail lookup, founder-initiated contact, bulk outreach, and saving for later with a named alternative (pitchspark_watch_pitch_v1). Routing conditions are unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources