BUILT WITH THE TWITTERAPI.IO TEAM
Back to Catalog
GET /v1/hn/story/commentsPack: social·MCP Tool: hn_story_comments

Hacker News Story Discussion Tree

Fetch full Hacker News story metadata and top-level technical comments by story ID.

API Key Price:$0.0005 / call
x402 Base USDC:$0.0010 / call
Partner Credit:eligible
1. Parameters & Controls
Numeric Hacker News item ID
Max top-level comments
curl -sG "https://api.agentapigate.ai/v1/hn/story/comments" \
  --data-urlencode "story_id=42237424" \
  --data-urlencode "limit=15" \
  --data-urlencode "format=md" \
  -H "Authorization: Bearer aag_live_YOUR_KEY" \
  -H "X-AAG-Max-Cost: 0.0100"
1-Click Agent IDE Install
+ Add Pack to Cursor
-97% tokens
# Hacker News Story Discussion Tree (`hn.story.comments`)
**count**: 15

### 1. 42237577
@jspahrsummers and I have been working on this for the last few months at Anthropic. I am happy to answer any questions people might have.
- id=42237577 | author=somnium_sn | created_at=2024-11-25T16:30:39.000Z | replies_count=29
### 2. 42237821
Good thread showing how this works: https://x.com/alexalbert__/status/1861079762506252723
- id=42237821 | author=benocodes | created_at=2024-11-25T16:56:37.000Z | replies_count=1
### 3. 42238029
i am curious: why this instead of feeding your LLM an OpenAPI spec?
- id=42238029 | author=outlore | created_at=2024-11-25T17:17:43.000Z | replies_count=3
### 4. 42238131
Thank you for creating this.
- id=42238131 | author=recsv-heredoc | created_at=2024-11-25T17:28:50.000Z | replies_count=0
### 5. 42238184
I’m glad they're pushing for standards here, literally everyone has been writing their own integrations and the level of fragmentation (as they also mention) and repetition going into building the infra around agents is super high.We’re building an in terminal coding agent and our next step was to connect to external services like sentry and github where we would also be making a bespoke integration or using a closed
- id=42238184 | author=ianbutler | created_at=2024-11-25T17:34:08.000Z | replies_count=2
### 6. 42238406
You can use MCP with Sourcegraph's Cody as wellhttps://sourcegraph.com/blog/cody-supports-anthropic-model-c...
- id=42238406 | author=ado__dev | created_at=2024-11-25T17:57:38.000Z | replies_count=0
### 7. 42238633
Hmm I like the idea of providing a unified interface to all LLMs to interact with outside data. But I don't really understand why this is local only. It would be a lot more interesting if I could connect this to my github in the web app and claude automatically has access to my code repositories.I guess I can do this for my local file system now?I also wonder if I build an LLM powered app, and currently simply to RAG
- id=42238633 | author=jascha_eng | created_at=2024-11-25T18:21:50.000Z | replies_count=5
### 8. 42238829
I don't understand the value of this abstraction.I can see the value of something like DSPy where there is some higher level abstractions in wiring together a system of llms.But this seems like an abstraction that doesn't really offer much besides "function calling but you use our python code".I see the value of language server protocol but I don't see the mapping to this piece of code.That's actually negative value 
- id=42238829 | author=WhatIsDukkha | created_at=2024-11-25T18:39:23.000Z | replies_count=2
### 9. 42238855
Are there any other Desktop apps other than Claude's supporting this?
- id=42238855 | author=orliesaurus | created_at=2024-11-25T18:41:37.000Z | replies_count=2
### 10. 42238872
How is this different from function calling libraries that frameworks like Langchain or Llamaindex have built?
- id=42238872 | author=orliesaurus | created_at=2024-11-25T18:42:44.000Z | replies_count=1
### 11. 42238999
Can someone please give examples of uses for this?
- id=42238999 | author=andrewstuart | created_at=2024-11-25T18:52:38.000Z | replies_count=1
### 12. 42239184
The Zed editor team collaborated with Anthropic on this, so you can try features of this in Zed as of today: https://zed.dev/blog/mcp
- id=42239184 | author=keybits | created_at=2024-11-25T19:11:09.000Z | replies_count=2
### 13. 42239310
One thing I dont understand.. does this rely on vector embeddings? Or how does the AI interact with the data? The example is a sqllite satabase with prices, and it shows claude being asked to give the average price and to suggest pricing optimizations.So does the entire db get fed into the context? Or is there another layer in between. What if the database is huge, and you want to ask the AI for the most expensive or
- id=42239310 | author=bentiger88 | created_at=2024-11-25T19:25:41.000Z | replies_count=2
### 14. 42239424
The Model Context server is similar to what we've built at Spice, but we've focused on databases and data systems. Overall, standards are good. Perhaps we can implement MCP as a data connector and tool.[1] https://github.com/spiceai/spiceai
- id=42239424 | author=lukekim | created_at=2024-11-25T19:38:10.000Z | replies_count=0
### 15. 42239451
I would love to integrate this into my platform of tools for AI models, Toolhouse [1], but I would love to understand the adoption of this protocol, especially as it seems to only work with one foundational model.[1] https://toolhouse.AI
- id=42239451 | author=orliesaurus | created_at=2024-11-25T19:41:31.000Z | replies_count=1