FastMCP seed raise pipeline tracker — syncs from Obsidian CRM, generates meeting
LocalAbout FastMCP seed raise pipeline tracker — syncs from Obsidian CRM, generates meeting
A FastMCP server for founders managing a seed-round investor pipeline from Obsidian CRM files. It syncs investor records, prepares meetings, logs interactions, and tracks pipeline health and follow-ups.
Key features
- 01Search investors by pipeline criteria
- 02View profiles and interaction history
- 03Generate tailored meeting preparation
- 04Update stages and log interactions
- 05Analyze pipeline and follow-up status
- 06Sync Obsidian CRM files
Use cases
- 01Review investor pipeline and contact priorities
- 02Prepare for an investor meeting
- 03Record investor conversations and stage changes
- 04Check follow-up compliance and pipeline health
MCP support
Exposes investor search, profiles, preparation, updates, analytics, and CRM sync as tools for MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEinvestor-relations-mcp
A FastMCP server for tracking your seed raise investor pipeline from Claude Code. Syncs from Obsidian vault CRM files, generates meeting prep documents, tracks interactions, and monitors follow-up compliance.
Built for founders raising a seed round who want to manage their pipeline conversationally without switching to a separate CRM.
Tools
| Tool | What it does |
|---|---|
investor_search | Search pipeline by name, stage, priority, or days since last contact |
investor_profile | Full investor profile + complete interaction history |
investor_prep | Meeting prep doc: portfolio fit, top 3 objections + rebuttals, stage-appropriate agenda |
investor_update | Update stage, log interactions, add investor-specific objections |
investor_analytics | Pipeline health: stage breakdown, committed count, follow-up compliance |
investor_sync | Re-sync from vault CRM markdown files |
Install
Open Claude Code, paste:
/plugin marketplace add adelaidasofia/investor-relations-mcp
/plugin install investor-relations-mcp@investor-relations-mcp
Then fill in pitch_config.yaml with your company's pitch positioning and global objections (drives the investor_prep tool), set INVESTOR_MCP_VAULT_CRM to your CRM folder, restart Claude Code, and run:
"Run investor_sync" "Show me my investor pipeline" "Prep me for my meeting with [name]"
Legacy install
pip install fastmcp pyyaml python-frontmatter
-
Clone:
git clone https://github.com/adelaidasofia/investor-relations-mcp.git cd investor-relations-mcp -
Fill in
pitch_config.yamlwith your company's pitch positioning and global objections. This is what drives theinvestor_preptool. -
Set environment variables:
export INVESTOR_MCP_VAULT_CRM="~/vault/CRM/" -
Register with Claude Code:
claude mcp add investor-relations -s user -- python3 /path/to/investor-relations-mcp/server.py -
Restart Claude Code, then sync your CRM:
"Run investor_sync" "Show me my investor pipeline" "Prep me for my meeting with [name]"
CRM file format
The server reads Obsidian markdown files where relationship: investor in the frontmatter:
---
relationship: investor
company: Acme Ventures
role: Partner
email: [email protected]
location: New York
priority: high
next_step: Follow up after pitch deck revision
---
Bio paragraph goes here.
## Timeline
- 2026-03-15 — Met at TechCrunch NYC event
- 2026-03-22 — Sent intro email with one-pager
- 2026-04-01 — Zoom call, strong interest in the model
pitch_config.yaml
This file configures your pitch positioning and global objection rebuttals:
company_name: "Your Company"
raise_amount: "$500K"
raise_description: "seed round"
pitch_positioning:
market: "Your market description..."
model: "How you make money..."
traction: "Your best proof point..."
ask: "Use of funds + runway..."
never_say: "Framings to avoid..."
global_objections:
- - "The market is too small"
- "Your rebuttal..."
Environment variables
| Variable | Default | Description |
|---|---|---|
INVESTOR_MCP_DB | ./investors.db | SQLite database path |
INVESTOR_MCP_VAULT_CRM | ~/vault/CRM/ | Folder with investor CRM files |
Pipeline stages
not_contacted → outreach_sent → response_received → meeting_scheduled → pitched → decision_pending → committed / passed
Stages can be customized in pitch_config.yaml.
Related MCPs
Same author, same architecture pattern (FastMCP, draft+confirm on writes where applicable, vault auto-export, MIT):
- slack-mcp - multi-workspace Slack
- imessage-mcp - macOS iMessage
- whatsapp-mcp - WhatsApp via whatsmeow
- google-workspace-mcp - Gmail / Calendar / Drive / Docs / Sheets
- apollo-mcp - Apollo.io CRM + sequences
- substack-mcp - Substack writing + analytics
- luma-mcp - lu.ma events
- parse-mcp - markitdown / Docling / LlamaParse router
- rescuetime-mcp - RescueTime productivity data
- graph-query-mcp - vault knowledge graph queries
- vault-sync-mcp - bidirectional vault sync
Telemetry
This plugin sends a single anonymous install signal to myceliumai.co the first time it loads in a Claude Code session on a given machine.
What is sent:
- Plugin name (e.g.
slack-mcp) - Plugin version (e.g.
0.1.0)
What is NOT sent:
- No user identifiers, names, emails, tokens, or API keys
- No file paths, message content, or anything from your work
- No IP address is stored after dedup processing
Why: Helps the maintainer know which plugins people actually install, so attention goes to the ones that get used.
Opt out: Set the environment variable MYCELIUM_NO_PING=1 before launching Claude Code. The hook will skip the network call entirely. Already-pinged installs leave a sentinel at ~/.mycelium/onboarded-<plugin> — delete it if you want to reset state.
License
MIT
Built by Mycelium AI.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.