funda-data

Name: funda-data
Author: himself65

1.0kinstalls351forks

How to install funda-data?

himself65/finance-skills/funda-data

$npx -y skills add himself65/finance-skills --skill funda-data

Installs into the current project.

Summary

Query Funda AI financial data via two surfaces: the MCP server at https://funda.ai/api/mcp for analyst-grade research synthesis (DCF, comps, earnings previews/recaps, sector deep-dives, SEC filings, transcripts, supply-chain mapping, ownership flow, macro framing) via the agent_c

Files · 1

View on GitHub

SKILL.md

1	# Funda AI Skill
2
3	Funda AI exposes two complementary surfaces backed by the same data:
4
5	\| Surface \| Best for \| Auth \| Output \|
6	\|---\|---\|---\|---\|
7	\| MCP `agent_chat` at `https://funda.ai/api/mcp` \| Research, analysis, synthesis \| OAuth (auto via `claude mcp add`) \| Synthesized text with disclaimer \|
8	\| REST `/v1/*` at `https://api.funda.ai` \| Raw structured data \| `FUNDA_API_KEY` Bearer \| JSON \|
9
10	Both require an active [Funda AI](https://funda.ai) subscription.
11
12	---
13
14	## Step 1: Decide Which Surface
15
16	\| User wants \| Surface \|
17	\|---\|---\|
18	\| DCF / comps walkthrough, sector view, transcript synthesis, company primer \| MCP \|
19	\| Earnings preview/recap with judgment, beat-miss decomposition, narrative framing \| MCP \|
20	\| Real-time or intraday quote, EOD price history \| REST \|
21	\| Raw options chain snapshot, greeks, GEX time series \| REST \|
22	\| Specific line item from a financial statement (single number, JSON) \| REST \|
23	\| 13F filings, insider trades, congressional trades as rows \| REST \|
24	\| News with structured sentiment / event timeline (JSON) \| REST \|
25	\| Bulk dataset downloads \| REST \|
26	\| AI-company hiring signals (OpenAI, Anthropic, Google, xAI) \| REST \|
27
28	Default to MCP for ambiguous research-style questions. Use REST when
29	the user wants machine-readable structured data — or when the MCP refuses
30	(real-time prices, raw quotes).
31
32	The MCP also refuses buy/sell calls, price targets, personalized
33	portfolio advice, tax/legal advice, and trade execution. Those are out of
34	scope for both surfaces — decline politely and don't fall through to REST
35	hoping for a different answer.
36
37	---
38
39	## Step 2: MCP Flow (Research)
40
41	### 2a. Verify the MCP is connected
42
43	```
44	!`claude mcp list 2>/dev/null \| grep -iE "^funda:" \|\| echo "FUNDA_MCP_NOT_CONNECTED"`
45	```
46
47	- A line starting with `funda:` → registered. The tool is callable as `mcp__funda__agent_chat`. Continue.
48	- `FUNDA_MCP_NOT_CONNECTED` → ask the user to install:
49	```bash
50	claude mcp add --transport http funda https://funda.ai/api/mcp
51	```
52	A browser tab opens for OAuth approval (1-hour token + 30-day refresh, auto-managed). The Claude Code session may need to be restarted before the tool registers.
53
54	### 2b. Frame the question
55
56	`agent_chat` is a fresh research turn with no cross-call memory — bake
57	the ticker, time horizon, and assumptions into the question text itself.
58
59	\| User wants \| Question shape \|
60	\|---\|---\|
61	\| Earnings preview \| "Preview MSFT's Q3 print Thursday — segment trends, where consensus is aggressive/conservative, beat/miss pattern." \|
62	\| Earnings recap \| "Walk through NVDA Q2: beat/miss by segment, guide vs consensus, transcript Q&A on data-center demand." \|
63	\| Sector deep-dive \| "Summarize the 2026 hyperscaler capex cycle — spending tiers by name, supplier exposure, gross-margin implications." \|
64	\| Supply chain \| "Map TSMC's customer concentration and N2 ramp risks — top three exposures by revenue." \|
65	\| Filing summary \| "Diff the new risk factors in PLTR's latest 10-K versus the prior year." \|
66	\| DCF \| "Walk through a DCF for NVDA assuming 25% data-center growth, 10% terminal margin, 9% WACC — surface the sensitivity table." \|
67	\| Macro \| "Where in the Dalio long-term debt cycle is the US, and what does that imply for duration positioning?" \|
68	\| Ownership \| "Has institutional ownership of CRWD shifted in the latest 13F filings — net buyers vs sellers?" \|
69
70	If the user gave only a ticker, ask one clarifying question to scope the
71	turn (preview? recap? primer? DCF?) before calling — vague questions burn
72	a turn and return vague answers.
73
74	If the user is following up on a prior Funda response, quote the relevant
75	paragraph back inside the new question; the agent has no memory of prior
76	calls.
77
78	For more example questions per topic, see `references/research-topics.md`.
79
80	### 2c. Call the tool
81
82	```
83	mcp__funda__agent_chat(question: "<full research question>")
84	```
85
86	Typical run is 15–60 seconds; the server streams progress notifications
87	throughout, so the client doesn't time

People who liked this also viewed

6 picks

Type

funda-data

1.0kinstalls351forks

View on GitHub

How to install funda-data?

himself65/finance-skills/funda-data

$npx -y skills add himself65/finance-skills --skill funda-data

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Funda AI Skill
2
3	Funda AI exposes two complementary surfaces backed by the same data:
4
5	\| Surface \| Best for \| Auth \| Output \|
6	\|---\|---\|---\|---\|
7	\| MCP `agent_chat` at `https://funda.ai/api/mcp` \| Research, analysis, synthesis \| OAuth (auto via `claude mcp add`) \| Synthesized text with disclaimer \|
8	\| REST `/v1/*` at `https://api.funda.ai` \| Raw structured data \| `FUNDA_API_KEY` Bearer \| JSON \|
9
10	Both require an active [Funda AI](https://funda.ai) subscription.
11
12	---
13
14	## Step 1: Decide Which Surface
15
16	\| User wants \| Surface \|
17	\|---\|---\|
18	\| DCF / comps walkthrough, sector view, transcript synthesis, company primer \| MCP \|
19	\| Earnings preview/recap with judgment, beat-miss decomposition, narrative framing \| MCP \|
20	\| Real-time or intraday quote, EOD price history \| REST \|
21	\| Raw options chain snapshot, greeks, GEX time series \| REST \|
22	\| Specific line item from a financial statement (single number, JSON) \| REST \|
23	\| 13F filings, insider trades, congressional trades as rows \| REST \|
24	\| News with structured sentiment / event timeline (JSON) \| REST \|
25	\| Bulk dataset downloads \| REST \|
26	\| AI-company hiring signals (OpenAI, Anthropic, Google, xAI) \| REST \|
27
28	Default to MCP for ambiguous research-style questions. Use REST when
29	the user wants machine-readable structured data — or when the MCP refuses
30	(real-time prices, raw quotes).
31
32	The MCP also refuses buy/sell calls, price targets, personalized
33	portfolio advice, tax/legal advice, and trade execution. Those are out of
34	scope for both surfaces — decline politely and don't fall through to REST
35	hoping for a different answer.
36
37	---
38
39	## Step 2: MCP Flow (Research)
40
41	### 2a. Verify the MCP is connected
42
43	```
44	!`claude mcp list 2>/dev/null \| grep -iE "^funda:" \|\| echo "FUNDA_MCP_NOT_CONNECTED"`
45	```
46
47	- A line starting with `funda:` → registered. The tool is callable as `mcp__funda__agent_chat`. Continue.
48	- `FUNDA_MCP_NOT_CONNECTED` → ask the user to install:
49	```bash
50	claude mcp add --transport http funda https://funda.ai/api/mcp
51	```
52	A browser tab opens for OAuth approval (1-hour token + 30-day refresh, auto-managed). The Claude Code session may need to be restarted before the tool registers.
53
54	### 2b. Frame the question
55
56	`agent_chat` is a fresh research turn with no cross-call memory — bake
57	the ticker, time horizon, and assumptions into the question text itself.
58
59	\| User wants \| Question shape \|
60	\|---\|---\|
61	\| Earnings preview \| "Preview MSFT's Q3 print Thursday — segment trends, where consensus is aggressive/conservative, beat/miss pattern." \|
62	\| Earnings recap \| "Walk through NVDA Q2: beat/miss by segment, guide vs consensus, transcript Q&A on data-center demand." \|
63	\| Sector deep-dive \| "Summarize the 2026 hyperscaler capex cycle — spending tiers by name, supplier exposure, gross-margin implications." \|
64	\| Supply chain \| "Map TSMC's customer concentration and N2 ramp risks — top three exposures by revenue." \|
65	\| Filing summary \| "Diff the new risk factors in PLTR's latest 10-K versus the prior year." \|
66	\| DCF \| "Walk through a DCF for NVDA assuming 25% data-center growth, 10% terminal margin, 9% WACC — surface the sensitivity table." \|
67	\| Macro \| "Where in the Dalio long-term debt cycle is the US, and what does that imply for duration positioning?" \|
68	\| Ownership \| "Has institutional ownership of CRWD shifted in the latest 13F filings — net buyers vs sellers?" \|
69
70	If the user gave only a ticker, ask one clarifying question to scope the
71	turn (preview? recap? primer? DCF?) before calling — vague questions burn
72	a turn and return vague answers.
73
74	If the user is following up on a prior Funda response, quote the relevant
75	paragraph back inside the new question; the agent has no memory of prior
76	calls.
77
78	For more example questions per topic, see `references/research-topics.md`.
79
80	### 2c. Call the tool
81
82	```
83	mcp__funda__agent_chat(question: "<full research question>")
84	```
85
86	Typical run is 15–60 seconds; the server streams progress notifications
87	throughout, so the client doesn't time

People who liked this also viewed

6 picks

Type