Heron Intelligence MCP

Connect Heron Intelligence — curated earnings call transcripts, management interviews, and a guided custom-research intake flow — directly to Claude or any Model Context Protocol-compatible AI client.

Highlights

Remote HTTPS transport — one URL, zero install for browser clients.
OAuth 2.1 — Dynamic Client Registration (RFC 7591) with PKCE S256.
Subsidiary & legacy-name resolution — search by ticker, name, or description; the server auto-maps spinoffs and rebrands to their current parent so coverage is never missed.
MCP tool annotations — read-only tools auto-approve in supporting clients; write tools always require explicit user confirmation.

Server

https://mcp.heron-intelligence.com/mcp

Skill (recommended — install first)

The repo ships a Claude Code Skill in skills/heron-intelligence/ that primes the model to use these tools automatically — without the user having to type "use Heron MCP to…". It also encodes formatting rules and the canonical provenance handling: Blue Heron (human-conducted), Heron AI (AI-conducted), and licensed third-party feeds such as Paragon — each named explicitly so the origin of every transcript stays visible to the user.

Install once per machine (org-wide):

cp -r skills/heron-intelligence ~/.claude/skills/

Restart Claude Code; verify with /list-skills. See skills/heron-intelligence/INSTALL.md for project-level install and team distribution.

Quickstart

Claude.ai (recommended)

Open Claude.ai → Settings → Connectors.
Click Add custom connector.
Enter the server URL above.
Click Authorize and sign in to Heron Intelligence.
Approve the requested scopes (mcp:read, mcp:write).
Start a new chat and ask Claude to use Heron Intelligence.

Claude Desktop

Add to ~/.claude/claude_desktop_config.json:

{
  "mcpServers": {
    "heron": {
      "command": "uvx",
      "args": ["--from", "HeronIntelligence-mcp", "heronintelligence-mcp"],
      "env": { "HERON_API_KEY": "hk-xxxx" }
    }
  }
}

Restart Claude Desktop.

Claude Code

claude mcp add heron \
  --command uvx \
  --args "--from HeronIntelligence-mcp heronintelligence-mcp" \
  -e HERON_API_KEY=hk-xxxx \
  -s user

Cursor / Windsurf

{
  "mcpServers": {
    "heron": {
      "command": "uvx",
      "args": ["--from", "HeronIntelligence-mcp", "heronintelligence-mcp"],
      "env": { "HERON_API_KEY": "hk-xxxx" }
    }
  }
}

Authentication

The remote MCP server uses OAuth 2.1 with PKCE (S256) and Dynamic Client Registration (RFC 7591). Connecting from Claude.ai:

Claude registers itself silently as an OAuth client.
You land on a Heron Intelligence consent page that names the application requesting access and asks for the Client ID and Client Secret issued to your seat. Get them from your account dashboard, or from your Heron administrator.
After consent, Claude receives a short-lived access token plus a refresh token. The refresh token is single-use and rotates on every refresh.
The server advertises the scopes mcp:read and mcp:write, and Claude requests both. Access to a given tool is decided by your own entitlements on the Heron Intelligence account behind the token.

For local stdio mode (Claude Desktop / Claude Code / Cursor / Windsurf), authenticate with a static API key via HERON_API_KEY. Request a key from your Heron Intelligence account dashboard.

Available tools

Read-only — research

Tool	Purpose
`whoami`	Returns the email of the user authenticated on the current MCP session.
`search_company`	Resolves a ticker, name, or description to a Heron Intelligence company id; auto-resolves subsidiaries and legacy names. Accepts a list of queries too, routed to the same batch path as `search_companies`, so resolving many names never needs a loop.
`search_companies`	Resolves MANY tickers/names/descriptions to company ids in one call; returns a deduped `resolved_ids` array. Preferred first step for watchlists, peer sets, or "compare X, Y, Z".
`search_people`	Semantic search over interviewed people (executives, channel contacts, former employees). Scope to one company with `company_id`, or to specific sources with `data_provider_names`; each person carries their provider attribution.
`get_company_overview`	Returns transcript counts, date range, and breakdown of available coverage for a company.
`get_companies_overview`	Coverage overview for many company ids in one call — batch coverage audit across a watchlist/peer set.
`get_recent_transcripts`	Lists transcript metadata with pagination and filters (due-diligence type, sentiment, call quality, free text). An empty page carries a `coverage` block: whether the window was widened for you, or that no coverage exists at all — with a `next_step` toward commissioned research when it does not.
`list_data_providers`	Lists the exact `data_provider_names` values the transcript and people tools accept, with how each source is produced. No backend call, no quota — call it instead of guessing a source name.
`get_transcript_content`	Returns transcript content, with optional payload selectors (`summary_only`, `limit_qa`, `max_qa_answer_chars`, `qa_ids`) to trim the response before the caller reads it.
`get_project_status`	Returns the current step, completed fields, and last artifact for a research project.

Read-only — watchlists

Tool	Purpose
`list_watchlists`	Lists every watchlist the user can see (own, firm-level, shared).
`get_watchlist`	Returns the companies in a watchlist, looked up by exact name (case-insensitive).

Read-only — alerts (saved monitoring rules)

Tool	Purpose
`list_alerts`	Lists every alert the user can see (own + firm-shared + team-shared) with `visibility` and `is_owner` flags.
`get_recent_alerts`	Returns alert firings across all visible alerts in the last N days (default 7, max 90).
`get_alert_history`	Returns the firing history of a single alert, most recent first.
`list_analysis_categories`	Lists the catalog categories valid for `type=analysis` alerts.
`list_report_templates`	Lists the report templates available to the user (user-own + system).

Write — custom research projects

Tool	Purpose
`start_research_project`	Creates a new research project record.
`define_research_brief`	Step 1 — refines the Research Brief artifact one user turn at a time.
`prepopulate_research_configuration`	Step 1 → Step 2 helper that pre-fills configuration fields from the brief.
`configure_research_project`	Step 2 — fills the project's canonical configuration fields.
`generate_research_questions`	Step 3 — generates and curates the project's topics and questions.
`submit_research_project`	Step 4 — submits the project to a Heron Intelligence representative.

Write — watchlists

Tool	Purpose
`create_watchlist`	Creates a new watchlist, optionally pre-populated with tickers or company names.
`rename_watchlist`	Renames an existing watchlist.
`add_to_watchlist`	Adds companies (by ticker or name) to an existing watchlist.
`remove_from_watchlist`	Removes companies from a watchlist.
`delete_watchlist`	Permanently deletes a watchlist (requires `confirm=true`).

Write — alerts

Tool	Purpose
`create_alert`	Creates a new alert (`notification` / `report` / `analysis`) with cadence- or threshold-based triggering.
`update_alert`	Partially updates an alert, including rename and scope replacement.
`pause_alert`	Pauses an active alert (stops firing without losing config).
`resume_alert`	Resumes a paused alert.
`delete_alert`	Soft-deletes an alert (requires `confirm=true`).

The alert tools were called drops before the Portal renamed the module. Only the alert names are listed in tools/list; a call that still uses an old name (list_drops, create_drop, ...) is served by the alert tool and its response carries renamed_to with the name to use.

Access by plan

Heron Events Platinum firms (firm_type = he_premium) do not get the Research Projects or Evasion tools: they are left out of tools/list and a call by name returns {"error": "tool_not_in_plan", ...}. The caller's tier comes from the API's GET /api/v1/auth/caller; when it cannot be read, nothing is restricted.

Example prompts

"How much research coverage does Heron Intelligence have on Amazon?"

"Find Heron Intelligence's research coverage for Facebook and show me what's available under their current corporate entity."

"Show me only the management due diligence transcripts available for Amazon from the last two quarters."

"Set up a weekly digest of new Energy-sector transcripts that mention margin compression."

"What alerts do I have set up? Show me the ones that fired this week."

"Add MSFT and NVDA to my Tech watchlist, then create an analysis alert on that watchlist using the Executive Assessment category."

Documentation

Full documentation: https://docs.heron-intelligence.com/overview/mcp

Privacy Policy

https://www.heron-intelligence.com/privacy-policy

The policy covers what is collected, how it is used and stored, third-party sharing, retention, and who to contact. What this MCP server itself handles:

Identity. OAuth resolves the connecting user to their Heron Intelligence account; whoami returns that email. No other profile data is read.
Tool arguments and results. Queries are forwarded to Heron Intelligence's own first-party API and the response is returned to the client. Nothing is proxied to a third party.
Operational records. One structured access line per request (method, path, status, latency, request id, and the resolved account), with the credential redacted out of the path before the line is written. Each tool call also records a usage event to Heron Intelligence's own backend — tool name, the arguments it was called with, a short summary of the result, status and duration — used for quota enforcement and support.
Not collected. Conversation content, chat history, memory, or user files. The server reads only the arguments a tool is called with.

Support

License

Released under the Apache License 2.0 — see LICENSE. Use of the hosted Heron Intelligence service requires an active account.

Metadata

Release files for HeronIntelligence-mcp 1.10.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for HeronIntelligence-mcp 1.10.1
File	Size	Uploaded	Provenance
heronintelligence_mcp-1.10.1.tar.gz	191.9 kB	Oct 22, 2026	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for HeronIntelligence-mcp 1.10.1
File	Interpreter	ABI	Platform	Reset
heronintelligence_mcp-1.10.1-py3-none-any.whl 90.6 kB Oct 22, 2026 Without provenance	Python 3	none	any	Details

Total release size: 282.5 kB

Release files / heronintelligence_mcp-1.10.1.tar.gz

Download URL	heronintelligence_mcp-1.10.1.tar.gz
Size	191.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`5fcb8bb069ffb3b837d17a3f1e8077601a087318ee68577517031d5f20fbf7c1`
BLAKE2b-256 checksum How to use checksums	`c4aa2df539028f45402c2c8f7830b674828836749a9c49acf82712dacf13efca`
Upload date	Oct 22, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`uv/0.13.5 {"installer":{"name":"uv","version":"0.13.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`

Release files / heronintelligence_mcp-1.10.1-py3-none-any.whl

Download URL	heronintelligence_mcp-1.10.1-py3-none-any.whl
Size	90.6 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`fbbf2d962efff82607b82f56907593761539e3ae64df587bc01963d3049e1157`
BLAKE2b-256 checksum How to use checksums	`0321f84d877392c9f884eaec24a0a64cdfb0c88844a5df4dd2b94049cbe9b207`
Upload date	Oct 22, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`uv/0.13.5 {"installer":{"name":"uv","version":"0.13.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`

Security for HeronIntelligence-mcp 1.10.1

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.