# PitchSpark: Pre-Seed & Seed Deal Flow (remote · pitchspark.io)

Search scored pre-seed & seed startups that are actively raising, by sector, stage or query.

- Trust score: 71/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `pitchspark.io`: 71/100 (this document), [markdown](https://verifymcp.io/servers/codytodd-ui-pitchspark/api-functions-pitchsparkmcp.md), [page](https://verifymcp.io/servers/codytodd-ui-pitchspark/api-functions-pitchsparkmcp)

## Channel facts

- Endpoint: `https://pitchspark.io/api/functions/pitchsparkMcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 6963 tokens (~464/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 8 days we've observed: 3 tool removals, 1 breaking changes, 0 auth/transport breaks, 14 additions.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the PitchSpark: Pre-Seed & Seed Deal Flow MCP server?

PitchSpark: Pre-Seed & Seed Deal Flow is a hosted endpoint at https://pitchspark.io/api/functions/pitchsparkMcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http codytodd-ui-pitchspark 'https://pitchspark.io/api/functions/pitchsparkMcp'
```

### Cursor

```json
{
  "mcpServers": {
    "codytodd-ui-pitchspark": {
      "url": "https://pitchspark.io/api/functions/pitchsparkMcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "codytodd-ui-pitchspark": {
      "type": "http",
      "url": "https://pitchspark.io/api/functions/pitchsparkMcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.codytodd-ui-pitchspark]
url = "https://pitchspark.io/api/functions/pitchsparkMcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "codytodd-ui-pitchspark": {
      "type": "remote",
      "url": "https://pitchspark.io/api/functions/pitchsparkMcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add codytodd-ui-pitchspark --url 'https://pitchspark.io/api/functions/pitchsparkMcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  codytodd-ui-pitchspark:
    url: "https://pitchspark.io/api/functions/pitchsparkMcp"
```

### Netclaw

```json
{
  "McpServers": {
    "codytodd-ui-pitchspark": {
      "Transport": "http",
      "Url": "https://pitchspark.io/api/functions/pitchsparkMcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add codytodd-ui-pitchspark -t streamable-http -u 'https://pitchspark.io/api/functions/pitchsparkMcp'
```

### Other

```json
{
  "mcpServers": {
    "codytodd-ui-pitchspark": {
      "type": "http",
      "url": "https://pitchspark.io/api/functions/pitchsparkMcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pitchspark_compare_pitches_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_pitch_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_score_v1” rewrote its description, which is the text the model reads
- [cosmetic] “pitchspark_save_search_v1” reworded the description of “min_score”
- [cosmetic] “pitchspark_search_pitches_v3” reworded the description of “min_score”

### 2026-11-20 (score 71, 0)

- [security] Tool “pitchspark_search_pitches_v3” rewrote its description, which is the text the model reads

### 2026-11-19 (score 71, 0)

- [security regression] Tool “pitchspark_search_pitches_v1” was removed
- [security regression] Tool “pitchspark_search_pitches_v2” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pitchspark_compare_pitches_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_decision_summary_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_pitch_v2” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_score_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_list_saved_searches_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_save_search_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_search_pitches_v3” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_thesis_fit_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_health_v1” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 100% → 94%
- [functional regression] Schema quality: 397 → 461
- [functional regression] Schema quality: 397 → 484
- [functional] Server version: 1.7.0 → 2.0.0
- [functional] Server version: 1.6.0 → 1.7.0
- [functional] New tool “pitchspark_compare_pitches_v1”
- [functional] New tool “pitchspark_get_decision_summary_v1”
- [functional] New tool “pitchspark_get_pitch_v2”
- [functional] New tool “pitchspark_get_score_v1”
- [functional] New tool “pitchspark_list_saved_searches_v1”
- [functional] New tool “pitchspark_list_watchlist_v1”
- [functional] New tool “pitchspark_pipeline_stage_v1”
- [functional] New tool “pitchspark_save_search_v1”
- [functional] New tool “pitchspark_search_pitches_v2”
- [functional] New tool “pitchspark_search_pitches_v3”
- [functional] New tool “pitchspark_thesis_fit_v1”
- [cosmetic] “pitchspark_save_search_v1” added an optional parameter “include_seen”
- [cosmetic] “pitchspark_search_pitches_v3” added an optional parameter “include_seen”
- [cosmetic] “pitchspark_search_pitches_v3” added an optional parameter “offset”
- [cosmetic] “pitchspark_search_pitches_v3” added an optional parameter “sort”
- [cosmetic] “pitchspark_save_search_v1” reworded the description of “query”
- [cosmetic] “pitchspark_save_search_v1” reworded the description of “sort”
- [cosmetic] “pitchspark_search_pitches_v3” reworded the description of “cursor”
- [cosmetic] “pitchspark_search_pitches_v3” reworded the description of “query”
- [cosmetic] “pitchspark_search_pitches_v3” made “query” optional

### 2026-11-18 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pitchspark_request_intro_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_search_pitches_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_submit_pitch_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_watch_pitch_v1” rewrote its description, which is the text the model reads

### 2026-11-17 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pitchspark_search_pitches_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_health_v1” rewrote its description, which is the text the model reads
- [functional] Server version: 1.5.0 → 1.6.0
- [functional] Server version: 1.4.2 → 1.5.0

### 2026-11-16 (score 71, +1)

- [security regression] Tool “pitchspark_find_startup_pitches_v1” was removed
- [security regression] Tool “pitchspark_health_v1” was removed
- [security regression] Tool “pitchspark_startup_pitch_details_v1” was removed
- [security regression] Tool “pitchspark_submit_v1” was removed
- [security regression] Tool “search_pitches” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pitchspark_get_health_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_get_pitch_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_request_intro_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_search_pitches_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_submit_pitch_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_watch_pitch_v1” rewrote its description, which is the text the model reads
- [functional regression] “pitchspark_get_pitch_v1” added a required parameter “pitch_id”, so existing callers break
- [functional regression] “pitchspark_get_pitch_v1” dropped the required parameter “id”
- [functional improvement] Schema quality: 1266 → 372
- [functional improvement] Schema quality: 1266 → 1073
- [functional] First check of Tool coverage: 100
- [functional] Server version: pitchsparkMcp@2026-11-15.6 → 1.4.2
- [functional] Server version: pitchsparkMcp@2026-11-15.5 → pitchsparkMcp@2026-11-15.6
- [functional] Server version: pitchsparkMcp@2026-11-14.20 → pitchsparkMcp@2026-11-15.5
- [functional] New tool “pitchspark_get_health_v1”
- [functional] New tool “pitchspark_get_pitch_v1”
- [functional] New tool “pitchspark_request_intro_v1”
- [functional] New tool “pitchspark_search_pitches_v1”
- [functional] New tool “pitchspark_submit_pitch_v1”
- [functional] New tool “pitchspark_watch_pitch_v1”
- [cosmetic] “pitchspark_request_intro_v1” reworded the description of “message”
- [cosmetic] “pitchspark_request_intro_v1” reworded the description of “pitch_id”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “green_flags”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “has_traction”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “hq_region”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “include_seen”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “limit”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “location”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “max_raise_usd”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “min_raise_usd”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “min_score”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “query”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “sector”
- [cosmetic] “pitchspark_search_pitches_v1” reworded the description of “stage”
- [cosmetic] “pitchspark_submit_pitch_v1” reworded the description of “company_name”
- [cosmetic] “pitchspark_submit_pitch_v1” reworded the description of “problem_statement”
- [cosmetic] “pitchspark_submit_pitch_v1” reworded the description of “raise_amount_usd”
- [cosmetic] “pitchspark_submit_pitch_v1” reworded the description of “sector”
- [cosmetic] “pitchspark_submit_pitch_v1” reworded the description of “stage”
- [cosmetic] “pitchspark_watch_pitch_v1” reworded the description of “pitch_id”

### 2026-11-15 (score 70, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pitchspark_find_startup_pitches_v1” rewrote its description, which is the text the model reads
- [functional] Server version: pitchsparkMcp@2026-11-14.19 → pitchsparkMcp@2026-11-14.20

### 2026-11-14 (score 70, −1)

- [security regression] Stability: unverified → fail
- [security regression] Tool “pitchspark_get_pitch_v1” was removed
- [security regression] Tool “pitchspark_search_v1” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “pitchspark_find_startup_pitches_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_startup_pitch_details_v1” rewrote its description, which is the text the model reads
- [security] Tool “pitchspark_health_v1” rewrote its description, which is the text the model reads
- [security] Tool “search_pitches” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 401 → 1210
- [functional regression] Schema quality: 401 → 1060
- [functional] Server version: pitchsparkMcp@2026-11-14.6 → pitchsparkMcp@2026-11-14.19
- [functional] Server version: pitchsparkMcp@2026-11-13.10 → pitchsparkMcp@2026-11-14.6
- [functional] New tool “pitchspark_submit_v1”
- [functional] New tool “pitchspark_find_startup_pitches_v1”
- [functional] New tool “pitchspark_startup_pitch_details_v1”
- [cosmetic] “pitchspark_find_startup_pitches_v1” added an optional parameter “include_seen”
- [cosmetic] “pitchspark_find_startup_pitches_v1” reworded the description of “limit”
- [cosmetic] “search_pitches” reworded the description of “limit”
- [cosmetic] “search_pitches” reworded the description of “location”
- [cosmetic] “search_pitches” reworded the description of “max_raise_usd”
- [cosmetic] “search_pitches” reworded the description of “min_raise_usd”
- [cosmetic] “search_pitches” reworded the description of “query”
- [cosmetic] “search_pitches” reworded the description of “sector”
- [cosmetic] “search_pitches” reworded the description of “stage”
- [cosmetic] Tool “pitchspark_find_startup_pitches_v1” changed its title: Find startup pitches on PitchSpark by sector, stage, traction or score → Find pre-seed and seed startup pitches for deal flow on PitchSpark
- [cosmetic] Tool “pitchspark_startup_pitch_details_v1” changed its title: Read one startup's full public pitch on PitchSpark → Read one startup's full public pitch on PitchSpark, by id from a search
- [cosmetic] Tool “pitchspark_health_v1” changed its title: Check PitchSpark availability → Check that PitchSpark pitch search is up
- [cosmetic] Tool “search_pitches” changed its title: Search PitchSpark startup pitches → Search PitchSpark startup pitches (deprecated)

## MCP tools (15)

### `pitchspark_get_pitch_v1` (~143 tokens)

Read one startup's full public pitch on PitchSpark, by id from a search

Read the full public pitch of one early-stage startup from a PitchSpark search, by pitch_id: problem and solution, traction, market size, business model, competitors, moat, highlights, team size, HQ region, the ask, green flags and pitchspark_score (PitchSpark's AI pitch score, 0-100; null when the pitch has not been scored). Use it to screen a pre-seed or seed deal in depth before requesting an intro. Founder claims are self-reported; financials, decks and founder contact details are not included.

Input parameters:

- `pitch_id` (string, required): The "id" of a search result, copied exactly.

Output parameters:

- `attribution` (string)
- `error` (object): Present only when the call failed (isError true).
- `pitch` (object)

### `pitchspark_get_health_v1` (~66 tokens)

Check that PitchSpark pitch search is up

Check that PitchSpark's pre-seed and seed deal-flow search is up before running a batch of startup searches. Returns {"status":"ok","version":"2.0.0"} and no pitch data. No key needed; uses none of the daily pitch allowance.

Output parameters:

- `error` (object): Present only when the call failed (isError true).
- `status` (string)
- `version` (string)

### `pitchspark_submit_pitch_v1` (~334 tokens)

Founders only: create a draft of your own startup pitch on PitchSpark

For founders raising a pre-seed or seed round: create a draft pitch on your own PitchSpark account from five facts (company name, sector, stage, raise amount in USD, a one-paragraph problem statement). The draft is not listed, searchable or scored until the founder completes it and submits it for review in Pitch Studio at the returned edit_url. Needs a founder submit token (pss_..., from PitchSpark Settings). Where OAuth is enabled, a token with the pitches:submit scope also works. Returns pitch_id, status "draft", company_name and edit_url.

Input parameters:

- `company_name` (string, required): The startup's name, one line, e.g. "Acme Robotics".
- `problem_statement` (string, required): One paragraph (40 to 1200 characters) on the problem and who has it. Its first sentence becomes the tagline.
- `raise_amount_usd` (number, required): Amount being raised in US dollars, e.g. 1500000.
- `sector` (string, required): Primary sector, e.g. "fintech". Keys: fintech, healthtech, saas, marketplace, ai_ml, consumer, enterprise, climate, edtech, crypto, biotech, hardware, gaming, real_estate, food_beverage, fashion, tra…
- `stage` (string, required): Stage of the round being raised, e.g. "seed".

Output parameters:

- `company_name` (string)
- `edit_url` (string)
- `error` (object): Present only when the call failed (isError true).
- `pitch_id` (string)
- `status` (string)

### `pitchspark_request_intro_v1` (~215 tokens)

Investors: ask a startup founder for an intro through PitchSpark

For investors who found a startup to invest in: ask the founders of one PitchSpark pitch (by pitch_id) to connect, with a short message, through PitchSpark's in-app contact flow. Founders reply inside PitchSpark; their contact details are never returned. Returns status (requested, already_requested or quota_exhausted), intro_id and next_steps. Needs a PitchSpark API key (psk_...) from an investor account (self-declared; PitchSpark does not verify accreditation), or where OAuth is enabled a token for one with the intros:write scope. PitchSpark does not verify investors or founders, does not recommend investments and takes no part in any resulting deal.

Input parameters:

- `message` (string, required): The investor's note to the founders: who they are and why they are interested. Up to 1000 characters are kept; emails, phone numbers, links and @handles are removed.
- `pitch_id` (string, required): The "id" of a search or details result, copied exactly.

Output parameters:

- `error` (object): Present only when the call failed (isError true).
- `intro_id` (string|null)
- `next_steps` (string)
- `status` (string)

### `pitchspark_watch_pitch_v1` (~159 tokens)

Investors: save a startup pitch to your PitchSpark saved pitches

For investors building a deal-flow shortlist: save one startup pitch (by pitch_id) to your PitchSpark saved pitches, to come back to on pitchspark.io. The founders are not contacted; the save counts as interest in their pitch statistics, where investors are numbered and never named. Saving again changes nothing. Returns status (watching, already_watching or limit_reached), pitch_id and next_steps. Needs a PitchSpark API key (psk_...) from an investor account (self-declared; PitchSpark does not verify accreditation), or where OAuth is enabled a token for one with the watchlist:write scope.

Input parameters:

- `pitch_id` (string, required): The "id" of a search or details result, copied exactly.

Output parameters:

- `error` (object): Present only when the call failed (isError true).
- `next_steps` (string)
- `pitch_id` (string)
- `status` (string)

### `pitchspark_get_pitch_v2` (~598 tokens)

Read one startup pitch with its score, roast and anonymised decisions

Read one startup pitch by id and choose what comes back with "sections": "pitch" (the full public pitch, the same object as pitchspark_get_pitch_v1), "score" (score and roast, as pitchspark_get_score_v1), "decisions" (anonymised decision aggregates by signed-in users, as pitchspark_get_decision_summary_v1). Default: all three. Use when: an investor wants the whole picture of one shortlisted pitch in one call. Prefer the single-purpose tools when you only need one part. Do not use for: searching (pitchspark_search_pitches_v3), founder contact details, financials, decks or data rooms (never returned), investment advice. Anonymous callers can use it under the daily allowance; dimension scores and analyses need an API key, and the decisions section an investor API key. Decision data from signed-in PitchSpark users needs a PitchSpark API key from an investor account (self-declared; PitchSpark does not verify accreditation): without one every decision block is available false with reason key_required. It is anonymised: counts of distinct people only, as bands ("5-9", "10-24", "25-49", "50+"), never who; shares and rates to the nearest 0.05; the pitch's founders, team and PitchSpark staff are never counted; guest and anonymous viewers are never counted; every block is withheld (reason below_min_k) when fewer than 5 distinct people are behind it, and a split (positive vs pass, rating bands) is withheld when any part of it would be under 5; no investor comment text is ever returned. Who is counted: ratings, reading time, sections and score views count ANY signed-in non-owner user (the writers check no account type), and likes, passes and pass reasons count signed-in users who swiped or gave pass feedback (also not restricted to investor accounts); only the caller of this tool must hold an investor key. Some fields are withheld pending a review (reason hidden_pending_review, or absent from a list): the team-related pass reasons and the pass rate (the likes-vs-passes thumbs b…

Input parameters:

- `id` (string, required): The pitch id from a search result ("id").
- `sections` (array): Which parts to return. Default ["pitch","score","decisions"].

Output parameters:

- `attribution` (string)
- `decisions` (object): Anonymised decision aggregates by signed-in PitchSpark users (not only investors); readable with investor API keys only (every block reason key_required otherwise). Counts are bands ("5-9", "10-24",…
- `error` (object): Present only when the call failed (isError true).
- `pitch` (object): pitchspark_get_pitch_v1's pitch object (same keys), present when sections includes "pitch".
- `score` (object)
- `sections` (array)

### `pitchspark_get_score_v1` (~342 tokens)

Get a startup pitch's PitchSpark AI score, dimension scores and roast commentary

Get PitchSpark's AI pitch score for one pitch: the composite (0-100), the six dimensions (market, problem, traction, moat, financials, team, each 0-100 with the model's analysis) and the Roast Room commentary when the pitch was roasted. Use when: an investor asks how PitchSpark rates a pitch, or where it is strong and weak. Prefer it over pitchspark_get_pitch_v2 when only the score is needed. Do not use for: scoring your own text (pitchspark_roast_text_v1, when enabled), what signed-in users decided (pitchspark_get_decision_summary_v1), investment advice. Limits of the data: the score is returned at any value; pitchspark_score is null only when the pitch has not been scored (dimensions_withheld "not_scored"). Dimensions and analyses need an API key (dimensions_withheld "key_required" without one). Roast text is filtered for personal attacks and contact details. Same access as pitchspark_get_pitch_v1: anonymous callers allowed under the daily allowance. Returns {"score":{pitch_id, company_name, pitchspark_score, scale, public_min, dimensions, dimensions_withheld, scoring_version, scored_at, roast}, "attribution"}. Each pitch this tool returns counts 1 against the daily pitch allowance (the one allowance every pitch tool shares), or 0 when the same API key (without a key, the same connection) already got that pitch today. Calls are logged, and each pitch returned is counted as a view.

Input parameters:

- `id` (string, required): The pitch id from a search result ("id").

Output parameters:

- `attribution` (string)
- `error` (object): Present only when the call failed (isError true).
- `score` (object)

### `pitchspark_get_decision_summary_v1` (~694 tokens)

What signed-in PitchSpark users decided about a startup pitch: anonymised pass reasons, ratings and engagement

Summarise how signed-in PitchSpark users (not only investors) responded to one pitch: positive (likes and superlikes) vs passes (the thumbs block, currently withheld pending review: reason hidden_pending_review), the rating distribution and average (out of 10, to the nearest 0.5), the top pass reasons and "why we passed" themes (the team-related reasons and the team theme are withheld pending review and never listed; shares are over the listed reasons), time spent, and which pitch sections and score dimensions users read. Use when: an investor (or a founder's assistant) wants the crowd signal behind a pitch before deciding. Prefer it over pitchspark_get_pitch_v2 when only decision data is needed. Do not use for: who passed or liked (never returned), investor comments (never returned), the AI score (pitchspark_get_score_v1). Decision data from signed-in PitchSpark users needs a PitchSpark API key from an investor account (self-declared; PitchSpark does not verify accreditation): without one every decision block is available false with reason key_required. It is anonymised: counts of distinct people only, as bands ("5-9", "10-24", "25-49", "50+"), never who; shares and rates to the nearest 0.05; the pitch's founders, team and PitchSpark staff are never counted; guest and anonymous viewers are never counted; every block is withheld (reason below_min_k) when fewer than 5 distinct people are behind it, and a split (positive vs pass, rating bands) is withheld when any part of it would be under 5; no investor comment text is ever returned. Who is counted: ratings, reading time, sections and score views count ANY signed-in non-owner user (the writers check no account type), and likes, passes and pass reasons count signed-in users who swiped or gave pass feedback (also not restricted to investor accounts); only the caller of this tool must hold an investor key. Some fields are withheld pending a review (reason hidden_pending_review, or absent from a list): the team-related…

Input parameters:

- `id` (string, required): The pitch id from a search result ("id").

Output parameters:

- `attribution` (string)
- `company_name` (string)
- `decisions` (object): Anonymised decision aggregates by signed-in PitchSpark users (not only investors); readable with investor API keys only (every block reason key_required otherwise). Counts are bands ("5-9", "10-24",…
- `error` (object): Present only when the call failed (isError true).
- `pitch_id` (string)

### `pitchspark_compare_pitches_v1` (~304 tokens)

Compare 2 to 4 startup pitches side by side: scores, traction, raise and decisions

Compare 2 to 4 pitches side by side: ask, stage, sector, HQ region, traction note, green flags, public score, dimension scores (keyed callers) and compact decision aggregates (likes vs passes, average rating, top pass reasons; investor API keys only, else reason key_required; each withheld below 5 distinct signed-in users, counts as bands; the likes-vs-passes block may be withheld with reason hidden_pending_review, and the team-related pass reasons are withheld pending review). Use when: an investor is choosing between shortlisted pitches. Do not use for: more than 4 pitches (run pitchspark_search_pitches_v3 sorted by score instead), full pitch text (pitchspark_get_pitch_v2). All ids must be distinct and resolvable: any id that is missing, not public or opted out answers NOT_FOUND for the whole call, and nothing is counted. The whole comparison is delivered or nothing is (a spent allowance answers RATE_LIMITED). Returns {"pitches":[...in the order given], "attribution"}. Each pitch this tool returns counts 1 against the daily pitch allowance (the one allowance every pitch tool shares), or 0 when the same API key (without a key, the same connection) already got that pitch today. Calls are logged, and each pitch returned is counted as a view.

Input parameters:

- `ids` (array, required): 2 to 4 distinct pitch ids.

Output parameters:

- `attribution` (string)
- `error` (object): Present only when the call failed (isError true).
- `pitches` (array)

### `pitchspark_thesis_fit_v1` (~378 tokens)

Rank startup pitches against an investment thesis, with a fit rationale

Rank PitchSpark pitches by how well they fit an investment thesis: either thesis text you pass, or the investor's saved thesis and preferences on PitchSpark (use_saved_thesis). Each result has a fit_score (0-100) and a rationale listing exactly which criteria matched. Use when: an investor asks "what fits my thesis". Prefer pitchspark_search_pitches_v3 for explicit filters. Do not use for: investment advice; the fit is a rule-based match, not a judgement. How it works (rule_based_v1, no model call): the thesis is read for sectors, stages, HQ regions and keywords (the same rules as search); a pitch earns points for each criterion it meets (sector 35, stage 25, region 10, keywords up to 30), scaled to the criteria the thesis names. Pitches that meet none are left out. Requires a PitchSpark API key (psk_...). The thesis text is never logged or stored. Returns {"pitches":[{card, fit_score, rationale}], "thesis", "method", "attribution"}. Up to 10 results (25 on a paid key). Each pitch this tool returns counts 1 against the daily pitch allowance (the one allowance every pitch tool shares), or 0 when the same API key (without a key, the same connection) already got that pitch today. Calls are logged, and each pitch returned is counted as a view.

Input parameters:

- `limit` (integer)
- `thesis_text` (string): The thesis in plain English, 20 to 2000 characters. Not with use_saved_thesis.
- `use_saved_thesis` (boolean): true: use the thesis and sector / stage / geography preferences saved on the key owner's PitchSpark profile. Not with thesis_text.

Output parameters:

- `attribution` (string)
- `error` (object): Present only when the call failed (isError true).
- `method` (string)
- `pitches` (array)
- `thesis` (object): The structured thesis that was matched: sectors, stages, regions, keywords, source.
- `truncated` (boolean)

### `pitchspark_list_watchlist_v1` (~160 tokens)

Investors: list the startup pitches saved to your PitchSpark watchlist

List the pitches the investor has saved on PitchSpark (in the app or with pitchspark_watch_pitch_v1), newest first: id, company name, stage, sector, when saved and the link. Use when: the investor asks what is on their watchlist or saved pitches. Do not use for: saving (pitchspark_watch_pitch_v1), searching. Requires a PitchSpark API key from an investor account (self-declared; PitchSpark does not verify accreditation). Pitches that are no longer public or whose founders opted out of AI agents are left out and counted in unavailable_count. Up to 50 items. Uses none of the daily pitch allowance. Read-only. Calls are logged.

Input parameters:

- `limit` (integer)

Output parameters:

- `error` (object): Present only when the call failed (isError true).
- `items` (array)
- `truncated` (boolean)
- `unavailable_count` (integer)

### `pitchspark_pipeline_stage_v1` (~205 tokens)

Investors: read where your pitches sit in your PitchSpark deal pipeline

Read the investor's own PitchSpark deal pipeline: for each pitch, its stage (sparked, deck_requested, in_conversation, due_diligence, invested), when it last moved and whether it is archived. Optionally one pitch_id. Use when: the investor asks where a deal stands. Do not use for: moving a deal (not available through this server; use PitchSpark), other investors' pipelines (never). Requires a PitchSpark API key from an investor account (self-declared; PitchSpark does not verify accreditation). Only the key owner's own rows are read. Notes and investment amounts are never returned (has_notes says whether there are notes). Pitches no longer public or opted out are left out (unavailable_count). Up to 50 items. Read-only; uses none of the daily pitch allowance.

Input parameters:

- `include_archived` (boolean)
- `pitch_id` (string): The pitch id from a search result ("id").

Output parameters:

- `error` (object): Present only when the call failed (isError true).
- `items` (array)
- `truncated` (boolean)
- `unavailable_count` (integer)

### `pitchspark_save_search_v1` (~858 tokens)

Save a startup search (query and filters) to re-run later

Save a search (the query and filters of pitchspark_search_pitches_v3) under the caller's API key, to list and re-run later with pitchspark_list_saved_searches_v1. Use when: the investor asks to save or remember a search. Do not use for: alerts (not delivered yet: saving does not send anything), running the search (pitchspark_search_pitches_v3). Requires a PitchSpark API key with the searches:write scope (keys without a scope list hold it). Idempotent: the same normalised query and filters under the same key returns the existing saved search (status "already_saved") and writes nothing new. At most 20 saved searches per key (status "limit_reached"); 50 saves per key per UTC day (RATE_LIMITED). Do not put personal data (names, emails, phone numbers, anything about a person) in "name" or "query": they are stored for up to 180 days. Emails and phone numbers that do appear are stored as [redacted]. Saved searches are deleted 180 days after they were last saved, and with the account. Returns {"status","saved_search","max_per_key","next_steps"}.

Input parameters:

- `created_within_days` (integer): Recency: listed on PitchSpark within this many days.
- `green_flags`: Traction signal: at least one of these founder-chosen green flags (e.g. "Profitable", "Signed LOI").
- `has_traction` (boolean): Traction signal: true = only pitches with a public traction note.
- `include_seen` (boolean): false (default): pitches this caller (API key, OAuth account, MCP session or anon id) was shown in the last 7 days are left out. true: neither leaves them out nor records this reply.
- `location`: HQ region key or list: us, canada, latam, uk, europe, mea, apac, global_remote.
- `max_raise_usd` (number): Raise at most this many US dollars (disclosed asks only).
- `min_raise_usd` (number): Raise at least this many US dollars (disclosed asks only).
- `min_score` (number): PitchSpark score at least this, 0 to 100 (pitches without a score are left out).
- `name` (string): A short label, e.g. "Seed fintech in Europe".
- `query` (string): Optional: what the investor is looking for, in plain language, 1 to 500 characters. Ranked by meaning when semantic ranking is available, by keyword + synonym otherwise (search_mode says which). A qu…
- `sector`: Sector key or list of up to 10 (primary or additional sector). Keys: fintech, healthtech, saas, marketplace, ai_ml, consumer, enterprise, climate, edtech, crypto, biotech, hardware, gaming, real_esta…
- `sort` (string): relevance (default: by meaning or keyword with a query, by a score and recency blend without one), score (public score, highest first), recency (newest submitted first: the date the pitch was submitt…
- `stage`: Funding stage or list. "early" means pre_seed, seed and series_a.
- `updated_within_days` (integer): Recency: pitch updated within this many days.

Output parameters:

- `error` (object): Present only when the call failed (isError true).
- `max_per_key` (integer)
- `next_steps` (string)
- `saved_search`
- `status` (string)

### `pitchspark_list_saved_searches_v1` (~123 tokens)

List the startup searches saved under your API key

List the searches saved with pitchspark_save_search_v1 under the caller's API key, newest first, each with the exact arguments to re-run it ("rerun": tool pitchspark_search_pitches_v3 and its arguments). Use when: the investor asks for their saved searches. Do not use for: running them (pass rerun.arguments to pitchspark_search_pitches_v3). Requires a PitchSpark API key (psk_...). Searches are per key, not per account. Read-only; uses none of the daily pitch allowance.

Output parameters:

- `error` (object): Present only when the call failed (isError true).
- `items` (array)
- `max_per_key` (integer)

### `pitchspark_search_pitches_v3` (~1213 tokens)

Search pre-seed and seed startup pitches by meaning

Find pre-seed and seed startups that are actively raising by what the investor means, not only the words used (e.g. "software that helps independent clinics get paid faster" finds revenue-cycle and payments pitches that never say "get paid"). Use when: an investor describes the kind of company they want in their own words (a problem, a customer, a business model), or wants a filtered deal-flow list sorted by score, recency, investor views or updates, or a browse with no query. This is PitchSpark's one search tool. Do not use for: reading one pitch in depth (pitchspark_get_pitch_v2), founder contact details, decks or data rooms (never returned), investment advice. The filters (sector, stage incl. "early", HQ region, raise range, minimum public score, traction, green flags, listed or updated within N days) narrow the list first; the query then ranks what is left. Only the sector argument filters by sector, and a list of sectors means any of them (OR). Sectors named in the query only boost the ranking, and several named together combine with AND ("climate hardware" ranks pitches filed under both highest); "interpretation.sectors_applied" marks each as filter or boost. For the most recent, newest or latest pitches pass sort "recency" with limit N and no query: newest submitted to PitchSpark first (created_at on each card), and include_seen true so pitches already shown are not skipped; a query that asks for the newest is ordered the same way. Ranking uses embeddings when they are available (similarity blended with the public score and recency) and falls back to keyword + synonym ranking when they are not. Without a query or sort the filtered pitches are browsed by a public score and recency blend (not newest first); a sort other than relevance orders by that key. Every reply states which in "search_mode" (semantic, mixed, keyword_fallback, browse or sorted) with "fallback_reason". Pitches this caller was shown in the last 7 days are left out unless include_seen is true…

Input parameters:

- `created_within_days` (integer): Recency: listed on PitchSpark within this many days.
- `cursor` (string): page.next_cursor from the previous call with the SAME query, filters, sort and include_seen. Not with offset.
- `green_flags`: Traction signal: at least one of these founder-chosen green flags (e.g. "Profitable", "Signed LOI").
- `has_traction` (boolean): Traction signal: true = only pitches with a public traction note.
- `include_seen` (boolean): false (default): pitches this caller (API key, OAuth account, MCP session or anon id) was shown in the last 7 days are left out. true: neither leaves them out nor records this reply.
- `limit` (integer): Page size. A value above the caller's tier ceiling is reduced to it.
- `location`: HQ region key or list: us, canada, latam, uk, europe, mea, apac, global_remote.
- `max_raise_usd` (number): Raise at most this many US dollars (disclosed asks only).
- `min_raise_usd` (number): Raise at least this many US dollars (disclosed asks only).
- `min_score` (number): PitchSpark score at least this, 0 to 100 (pitches without a score are left out).
- `offset` (integer): Skip this many results instead of a cursor. Not with cursor.
- `query` (string): Optional: what the investor is looking for, in plain language, 1 to 500 characters. Ranked by meaning when semantic ranking is available, by keyword + synonym otherwise (search_mode says which). A qu…
- `sector`: Sector key or list of up to 10 (primary or additional sector). Keys: fintech, healthtech, saas, marketplace, ai_ml, consumer, enterprise, climate, edtech, crypto, biotech, hardware, gaming, real_esta…
- `sort` (string): relevance (default: by meaning or keyword with a query, by a score and recency blend without one), score (public score, highest first), recency (newest submitted first: the date the pitch was submitt…
- `stage`: Funding stage or list. "early" means pre_seed, seed and series_a.
- `updated_within_days` (integer): Recency: pitch updated within this many days.

Output parameters:

- `attribution` (string)
- `coverage` (object)
- `error` (object): Present only when the call failed (isError true).
- `fallback_reason`: Why the reply is not fully semantic; null when search_mode is semantic.
- `interpretation` (object)
- `low_confidence` (boolean): true when no pitch cleared the relevance floor: only the closest few (at most 3) are shown, with "message".
- `message` (string): Only with low_confidence true: "No strong matches. Closest results shown."
- `page` (object)
- `pitches` (array)
- `search_mode` (string): How this reply was ranked: semantic (by meaning), mixed (by meaning, then keyword matches among pitches without a current embedding), keyword_fallback (keyword + synonym matching), browse (no query:…
- `seen_excluded` (integer)
- `sort` (string)
- `suggestions` (array): Only when fewer than 3 results: which filters cost the most and how many results dropping each gives (e.g. "Dropping min_score gives 14 results."), counted without using any of your allowance.
- `truncated` (boolean)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/codytodd-ui-pitchspark/api-functions-pitchsparkmcp#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 71
- 2026-11-19: 71
- 2026-11-18: 71
- 2026-11-17: 71
- 2026-11-16: 71
- 2026-11-15: 70
- 2026-11-14: 70
- 2026-11-13: 71

## Common questions

### What is the PitchSpark: Pre-Seed & Seed Deal Flow MCP server?

PitchSpark: Pre-Seed & Seed Deal Flow is an MCP server listed in the public MCP registry as io.github.codytodd-ui/pitchspark. Search scored pre-seed & seed startups that are actively raising, by sector, stage or query. This page covers its hosted endpoint (https://pitchspark.io/api/functions/pitchsparkMcp).

### Is the PitchSpark: Pre-Seed & Seed Deal Flow MCP server safe to use?

PitchSpark: Pre-Seed & Seed Deal Flow scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the PitchSpark: Pre-Seed & Seed Deal Flow MCP server expose?

PitchSpark: Pre-Seed & Seed Deal Flow exposes 15 tools: pitchspark_get_pitch_v1, pitchspark_get_health_v1, pitchspark_submit_pitch_v1, pitchspark_request_intro_v1, pitchspark_watch_pitch_v1, and 10 more. Their descriptions and schemas cost roughly 5,792 tokens of context every time the server is loaded.

### Does the PitchSpark: Pre-Seed & Seed Deal Flow MCP server require authentication?

No. We connected to PitchSpark: Pre-Seed & Seed Deal Flow without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the PitchSpark: Pre-Seed & Seed Deal Flow MCP server still maintained?

PitchSpark: Pre-Seed & Seed Deal Flow is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the PitchSpark: Pre-Seed & Seed Deal Flow MCP server?

VerifyMCP ran 13 checks on PitchSpark: Pre-Seed & Seed Deal Flow, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://pitchspark.io/api/functions/pitchsparkMcp
- Website: https://pitchspark.io/
- Changelog RSS feed: https://verifymcp.io/servers/codytodd-ui-pitchspark/api-functions-pitchsparkmcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/codytodd-ui-pitchspark/api-functions-pitchsparkmcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/codytodd-ui-pitchspark/api-functions-pitchsparkmcp.json
- HTML version of this page: https://verifymcp.io/servers/codytodd-ui-pitchspark/api-functions-pitchsparkmcp
