Is anyone working on a "catalog" of MCP servers? Searching on Github is not exactly the best way to discover these.
There are multiple directories already. I listed some in my notes: https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33....
MCP server for Ghidra
41–50 of 77 posts
Re: MCP server for Ghidra
#42For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.
Re: MCP server for Ghidra
#43For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.
LLMs are autoregressive models. However, the notion of order in ASTs might be nonexistent, especially for parallel branches of computation/control flow.
You could attempt to untangle each branch into N sequences, but this would erase control-flow information.
Even when there is an objective ordering of the children of every node, you still have four traversal options: {preorder, postorder} × {BF, DF}.
Note: For children lacking an objective ordering, you might apply generic rules to define a traversal order, but you’d end up with as many depth-first traversals as there are possible orders—essentially a crude heuristic. If you want the evaluation order to be dynamic at each step (e.g., using RL), the complexity grows geometrically worse. That’s been my experience tinkering with a custom AST DSL for ARC-AGI.
Re: MCP server for Ghidra
#44For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.
LLMs process information in a strictly sequential manner. It's their core capability and what makes them feel so anthropomorphic.
Re: MCP server for Ghidra
#45For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.
LLMs process information in a strictly sequential manner. It's their core capability and what makes them feel so anthropomorphic.
> LLMs process information in a strictly sequential manner.
"LLMs" as a class do not. Most LLMs, because most LLMs are autoregressive models, but diffusion LLMs exist and are not sequential in the way that autoregressive models are.
> It's their core capability
Being sequential is not a capability at all, much less a core one defining Large Language Models.
> and what makes them feel so anthropomorphic.
I disagree with this, too; I think what makes LLMs "feel so anthropomorphic" is the fact that most humans are very focused on language in perceiving other humans as human, and LLMs' output (as their name suggests) models human use of language, directly targeting a key feature used to identify something as human-like.
Re: MCP server for Ghidra
#46For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.
LLMs are autoregressive models. However, the notion of order in ASTs might be nonexistent, especially for parallel branches of computation/control flow. You could attempt to untangle each branch into N sequences, but this would erase control-flow information. Even when there is an objective ordering of the children of every node, you still have four traversal options: {preorder, postorder} × {BF, DF}. Note: For child…
> LLMs are autoregressive models.
Most LLMs are autoregressive models, but exceptions exist, e.g., Mercury [0] is a diffusion LLM.
Re: MCP server for Ghidra
#47For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.
LLMs are autoregressive models. However, the notion of order in ASTs might be nonexistent, especially for parallel branches of computation/control flow. You could attempt to untangle each branch into N sequences, but this would erase control-flow information. Even when there is an objective ordering of the children of every node, you still have four traversal options: {preorder, postorder} × {BF, DF}. Note: For child…
Cool to hear you've worked on ARC-AGI — I poked with it too. You’re totally right about the messy traversal space, especially with parallel branches. What feels ambiguous at the token level becomes structured ambiguity in the AST — and that’s progress.
My hunch is that LLMs don’t need to solve the whole traversal space — they just need a clean, abstract interface. Even parallel branches can be normalized into a schema that the model can reason over consistently. And in practice, you rarely need full recursion or a complete tree walk to understand a node — but having that option unlocks deeper comprehension when it counts.
This kind of structural understanding would also massively improve Copilot-style tools, especially for less popular libraries where token-level familiarity breaks down. If models could reason over types and structure instead of guessing based on frequency, completions would be a lot more reliable outside the top 1% of APIs.
Re: MCP server for Ghidra
#48For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.
LLMs process information in a strictly sequential manner. It's their core capability and what makes them feel so anthropomorphic.
Not fully.
The point of transformer attention is cross-wise processing of tokens that computes their relationship to each other at multiple levels of abstraction. That's why LLMs can read so fast: they're processing all the input tokens in parallel.
LLMs emit tokens in a sequential manner at the level of the outer loop, but clearly inside the activations is a non-sequential map of the entire planned output, otherwise they wouldn't be able to make coherent sentences or speak German (which puts verbs at the end).
Re: MCP server for Ghidra
#49Is anyone working on a "catalog" of MCP servers? Searching on Github is not exactly the best way to discover these.
Re: MCP server for Ghidra
#50my experience with just copying and pasting things from ghidra into LLMs and asking it to figure it out wasn't so successful. it'd be cool to have benchmarks for this stuff though.
I've been thinking on how to build a benchmark for this stuff for a while, and don't have a good idea other than LLM-as-judge (which quickly gets messy). I guess there's a reason why current neural decompilation attempts are all evaluated on "seemingly meaningless" benchmarks like "can it recompile without syntax error" or "functional equivalence of recompilation" etc.
[dead]