The MCP Server of You: Building a Personal Knowledge Power for Kiro IDE
A Kiro IDE Power that reads your personal markdown vault via MCP and injects the relevant context before your first prompt. Automatic, every session, no cloud dependency.
The MCP Server of You: Building a Personal Knowledge Power for Kiro IDE
In this post I'm going to walk you through how I built kiro-recall,
a Kiro IDE Power that loads your personal knowledge vault into every
session before you type a single word.
a Kiro IDE Power that loads your personal knowledge vault into every
session before you type a single word.
We'll cover why I built it, how it works, and how you can install
and test it yourself.
and test it yourself.
I'm getting old, and as I get older, I find my brain races faster than it ever has, because I have gained more and more knowledge as the years have dragged on ceaselessly.
I needed to go back to filing my thoughts.
I started with a notepad with way too many unsaved tabs. Great. Now I can't remember what I wrote on every single tab, let alone find them on my PC if I closed them down.
I needed a solution - a digital Zettelkasten folder or "second brain" vault seemed to solve that problem, so I built one in Obsidian .
During the development of the Power though, I discovered all I needed
Obsidian for was the inspiration. I needed to see the shape of how
these things were constructed.
Obsidian for was the inspiration. I needed to see the shape of how
these things were constructed.
Turns out a vault is just a folder. Plain markdown files on your own disk,
organised in a way that makes sense to you. No app required to read
them, no proprietary format locking you in, no cloud sync needed.
Any text editor can open them. Any MCP server can read them.
organised in a way that makes sense to you. No app required to read
them, no proprietary format locking you in, no cloud sync needed.
Any text editor can open them. Any MCP server can read them.
That realisation is what made kiro-recall possible. If the vault is
just a folder, you can point an MCP server at it, read the files
directly, and inject them into a Kiro session without Obsidian ever
being involved. Obsidian is still great for browsing your notes
visually, the graph view, backlinks, and plugin ecosystem are
genuinely useful. But it's optional. The vault works without it.
just a folder, you can point an MCP server at it, read the files
directly, and inject them into a Kiro session without Obsidian ever
being involved. Obsidian is still great for browsing your notes
visually, the graph view, backlinks, and plugin ecosystem are
genuinely useful. But it's optional. The vault works without it.
What we're building
kiro-recall is the MCP Server of You.
Your decisions, your knowledge, your project context, loaded from your
own machine into every Kiro session automatically before your first
prompt reaches the model.
own machine into every Kiro session automatically before your first
prompt reaches the model.
Kiro's steering files are unreliable.
I found this out the hard way. I had steering files configured with
single interaction. They still got ignored. Kiro would generate code
in broken language causing syntax errors, forget architectural decisions
I'd documented, and ask me to re-explain context I'd already written down.
inclusion: always, the mode that's supposed to load them into everysingle interaction. They still got ignored. Kiro would generate code
in broken language causing syntax errors, forget architectural decisions
I'd documented, and ask me to re-explain context I'd already written down.
After a Kiro update introduced Agent Skills, the problem got worse. Users
started reporting on GitHub that project steering files were failing
to load entirely, with the AI ignoring
of generic task instructions.
started reporting on GitHub that project steering files were failing
to load entirely, with the AI ignoring
inclusion: always in favourof generic task instructions.
Every new session I was back to re-establishing who I am, what the
project is, what decisions were already made.
project is, what decisions were already made.
kiro-recall replaces that with a hook-based context injection system.
A session start hook fires on your first prompt. Before your message
reaches the model, it reads your personal knowledge vault from disk
via MCP and injects the relevant notes as context. Not steering files.
Not a prompt you paste in every session. Your actual notes, loaded
automatically, every time.
reaches the model, it reads your personal knowledge vault from disk
via MCP and injects the relevant notes as context. Not steering files.
Not a prompt you paste in every session. Your actual notes, loaded
automatically, every time.
You do nothing. It just happens.
The difference is architectural. Steering files sit in your workspace
and hope the model reads them. kiro-recall uses a hook - it fires on
the
anything. The context is already in the session before your first word.
and hope the model reads them. kiro-recall uses a hook - it fires on
the
promptSubmit event, which means it runs before Kiro can ignoreanything. The context is already in the session before your first word.
The vault is plain markdown files. No cloud dependency for reading your
own notes. No data leaving your machine.
v0.1.0 ships four hooks:
own notes. No data leaving your machine.
v0.1.0 ships four hooks:
| Hook | Trigger | What it does |
|---|---|---|
| Session Start | Every first prompt | Reads vault, injects context |
| /recall | User triggered | Writes a structured note to 00-inbox/ |
| Vault Scaffold | User triggered | Creates the standard folder structure |
| /promote | User triggered | Reformats an inbox note as a Zettelkasten permanent note |
The architecture is intentionally minimal. No compiled code. No runtime
dependencies beyond the MCP server. Every hook is a JSON file with an
procedure using MCP tool calls.
dependencies beyond the MCP server. Every hook is a JSON file with an
askAgent prompt that instructs the model to execute a numberedprocedure using MCP tool calls.
This isn't a new idea. Developers have been pointing Claude Code at
Obsidian vaults for months, and the consensus is consistent: targeted
context beats re-explaining everything from scratch every time.
Obsidian vaults for months, and the consensus is consistent: targeted
context beats re-explaining everything from scratch every time.
And apparently, it saves you tokens and credits.
That might seem counterintuitive. You're adding context, so shouldn't
that cost more? The saving comes from what you stop doing.
that cost more? The saving comes from what you stop doing.
Before I built kiro-recall, every Kiro session started the same way.
I'd open a workspace, type my first prompt, and immediately hit a wall.
Kiro didn't know what I was building, what decisions I'd already made,
or what stack I was using. So I'd spend the first few exchanges just
getting it up to speed. Sometimes I'd paste in background. Sometimes
I'd answer clarifying questions. Sometimes I'd just watch it confidently
do the wrong thing because it had no context to work from.
I'd open a workspace, type my first prompt, and immediately hit a wall.
Kiro didn't know what I was building, what decisions I'd already made,
or what stack I was using. So I'd spend the first few exchanges just
getting it up to speed. Sometimes I'd paste in background. Sometimes
I'd answer clarifying questions. Sometimes I'd just watch it confidently
do the wrong thing because it had no context to work from.
That re-establishment isn't free. Every clarification, every correction,
every "no, I already decided to use X not Y" costs tokens. It happens
at the start of every session, every day, across every project.
every "no, I already decided to use X not Y" costs tokens. It happens
at the start of every session, every day, across every project.
kiro-recall front-loads a small, targeted context injection once per
session. Atomic permanent notes are concise by design, one idea per
note. The session hook runs once and stops. What it replaces is
typically far more expensive in both credits and time, but that's
one of the things I want testers to actually measure and report back on. I will be conducting my own A/B testing in regards to this.
session. Atomic permanent notes are concise by design, one idea per
note. The session hook runs once and stops. What it replaces is
typically far more expensive in both credits and time, but that's
one of the things I want testers to actually measure and report back on. I will be conducting my own A/B testing in regards to this.
The difference with kiro-recall specifically is the hook. Every other
approach still requires you to remember to load the context.
kiro-recall makes it impossible to forget.
approach still requires you to remember to load the context.
kiro-recall makes it impossible to forget.
How it works
The vault structure
The scaffold hook creates this structure on first run, wherever you
point it. Your vault can live anywhere on your machine, a dedicated
folder in Documents, alongside your dev projects, wherever makes sense
for you. You configure the path once in
point it. Your vault can live anywhere on your machine, a dedicated
folder in Documents, alongside your dev projects, wherever makes sense
for you. You configure the path once in
mcp.json and that's it.1
2
3
4
5
6
7
8
9
vault/
├── 00-inbox/ # /recall writes here
├── 01-projects/ # one file or subfolder per active project
├── 02-job-search/
├── 03-learning/
├── 04-knowledge/
├── 05-community/
├── 06-permanent/ # atomic Zettelkasten notes — loaded every session
└── 07-templates/
This structure is opinionated. It's based on my own workflow as an
AWS Community Builder juggling job applications, learning, and community
work alongside dev projects. The folders that actually drive kiro-recall's
behaviour are only three:
The rest is suggested organisation. Rename them, ignore them, add your own.
The vault is just a folder, it's yours.
AWS Community Builder juggling job applications, learning, and community
work alongside dev projects. The folders that actually drive kiro-recall's
behaviour are only three:
00-inbox/, 01-projects/, and 06-permanent/.The rest is suggested organisation. Rename them, ignore them, add your own.
The vault is just a folder, it's yours.
It starts like this...
Relevance detection
The session start hook runs a four-stage Relevance Detector before injecting anything:
Stage 1 - Primary signal. The hook extracts the workspace folder
name (e.g.
or subfolder exists in
project note plus all permanent notes and stops.
name (e.g.
kiro-recall from C:\Dev\kiro-recall or/Users/mike/projects/kiro-recall) and checks whether a matching fileor subfolder exists in
01-projects/. If it finds one, it loads thatproject note plus all permanent notes and stops.
Stage 2 - Secondary signal. If no primary match, it scans the paths
of all open files in the workspace. Any path segment that matches a
project folder name in
checks
this stage.
of all open files in the workspace. Any path segment that matches a
project folder name in
01-projects/ resolves the project. It alsochecks
.kiro/steering/ for a project field as a fallback withinthis stage.
Stage 3 - Fallback. No project match found. Load all permanent notes
from
from
06-permanent/ and inject those.Stage 4 - Cold vault. If
empty, skip injection entirely and show a warm onboarding message
instead of an error.
06-permanent/ and 00-inbox/ are bothempty, skip injection entirely and show a warm onboarding message
instead of an error.
A generic name guard runs before Stage 1. Workspace names like
secondary signals. This prevents false matches on common folder names.
src,dev, app, repo skip primary matching entirely and go straight tosecondary signals. This prevents false matches on common folder names.
The hook files
Each hook is a
.kiro.hook JSON file. Here's the structure:1
2
3
4
5
6
7
8
9
10
11
{
"name": "kiro-recall: Session Start",
"version": "1.0.0",
"when": {
"type": "promptSubmit"
},
"then": {
"type": "askAgent",
"prompt": "..."
}
}
The
hook includes a once-per-session guard. On the first prompt it runs
the full Relevance Detector and injects context. On every subsequent
prompt in the same session it exits immediately. You get context once,
cleanly, at the start.
promptSubmit event fires on every prompt, so the session starthook includes a once-per-session guard. On the first prompt it runs
the full Relevance Detector and injects context. On every subsequent
prompt in the same session it exits immediately. You get context once,
cleanly, at the start.
The capture and promote hooks use
quietly until you need them, type
a note, or
knowledge base.
userTriggered instead. They sitquietly until you need them, type
/recall mid-session to capturea note, or
/promote to move an inbox note into your permanentknowledge base.
The MCP dependency
kiro-recall wraps @bitbonsai/mcpvault
for vault access.
for vault access.
The original choice was smithery-ai/mcp-obsidian, but it only exposed
two tools and had no active maintenance. mcpvault ships 14 tools
including
your vault. It reads any directory of markdown files directly from disk,
which means no Obsidian install required and no dependency on any
proprietary format.
two tools and had no active maintenance. mcpvault ships 14 tools
including
write_note, search_notes, read_multiple_notes, andmove_note, everything the hooks need to read, write, and reorganiseyour vault. It reads any directory of markdown files directly from disk,
which means no Obsidian install required and no dependency on any
proprietary format.
One configuration line is all it needs:
1
2
3
4
5
6
7
8
{
"mcpServers": {
"mcpvault": {
"command": "npx",
"args": ["-y", "@bitbonsai/mcpvault", "YOUR_VAULT_PATH_HERE"]
}
}
}
Replace
you're connected. The vault path is the only configuration required.
Everything else is derived from the folder structure at runtime.
YOUR_VAULT_PATH_HERE with the path to your vault folder andyou're connected. The vault path is the only configuration required.
Everything else is derived from the folder structure at runtime.
The promote flow
The
/promote hook is the most interesting piece of v0.1.0./recall is fast and low-friction by design. You dump a rough noteinto
00-inbox/ and move on. But rough notes don't load well ascontext, they're messy, multi-topic, and hard for the model to use.
Permanent notes need to be atomic. One idea, clearly stated, with
connections to related concepts.
/promote does that reformatting for you. It lists your inbox notes,you pick one, and the hook rewrites it as a proper Zettelkasten permanent
note with a fixed structure:
1
2
3
4
5
6
7
8
9
10
11
12
13
{Idea Title}
# The idea
{single atomic statement, 1-2 sentences}
# Why it matters
{significance or future relevance, 1-2 sentences}
# Connected to
{[[wikilink]] references}
# Source
{project}, {session description}, {YYYY-MM-DD}
The filename is derived from the idea title using kebab-case with no
date prefix. Permanent notes are evergreen, the filename reflects the
idea, not when it was written. A note called
meaningful in two years. A note called
is not.
date prefix. Permanent notes are evergreen, the filename reflects the
idea, not when it was written. A note called
relevance-detection-via-workspace-name.md is still findable andmeaningful in two years. A note called
2026-03-20-session-notes.mdis not.
After writing to
in a code block so nothing is lost. If the delete fails after a
successful write, it warns you but doesn't roll back. The promoted
note already exists in permanent, so the worst case is a duplicate
in your inbox that you can delete manually.
06-permanent/, the hook deletes the original from00-inbox/. If the write fails, it surfaces the full reformatted notein a code block so nothing is lost. If the delete fails after a
successful write, it warns you but doesn't roll back. The promoted
note already exists in permanent, so the worst case is a duplicate
in your inbox that you can delete manually.
nb: this also deletes the base file keeping the inbox clean.
Installing it
kiro-recall ships as a Kiro Power and is installable right now directly
from GitHub.
from GitHub.
- Open Kiro IDE and go to the Powers panel
- Click Add power from GitHub
- Paste
https://github.com/mikeartee/kiro-recall - Once installed, open the Powers config and update the
power-kiro-recall-mcp-obsidianentry - replaceYOUR_VAULT_PATH_HEREwith the full path to your vault folder - Restart Kiro or reconnect the MCP server from the MCP Servers panel
- Trigger the Vault Scaffold hook once from the Hooks panel to create your folder structure
- Start a new session - the session start hook fires automatically on your first prompt
From the next session onwards, context loads automatically.
What it produces
After the session start hook runs, you see exactly one line:
1
Loaded kiro-recall note (primary match) + 3 permanent notes.
No file paths. No diagnostic output. Just a confirmation of what was loaded and how it was matched.
After
/recall:1
Note saved: 2026-03-20-kiro-recall-promote-flow-decision.md. It's in your inbox whenever you're ready to review it.
After
/promote:1
Promoted to `06-permanent/relevance-detection-via-workspace-name.md`.
The vault fills itself as a side effect of your normal dev workflow. Over time it becomes a searchable record of every decision, pattern, and insight across all your projects.
I need testers. Windows and Mac both welcome.
Some things I want feedback on:
- Does it work on your machine?
- Does the vault context actually change how your sessions feel?
- Does it use less credits in Kiro IDE on tasks?
- What would you add or change?
- Was it easy to install?
Install via Add Power from GitHub in Kiro IDE:
https://github.com/mikeartee/kiro-recall
https://github.com/mikeartee/kiro-recall
About the author
Mike Rewiri-Thorsen is an AWS Community Builder in the AI Engineering
track, based in Palmerston North, Aotearoa New Zealand. He builds agentic AI tooling and cloud infrastructure, and shares the work publicly as he goes.
track, based in Palmerston North, Aotearoa New Zealand. He builds agentic AI tooling and cloud infrastructure, and shares the work publicly as he goes.
References
bitbonsai. (2026). mcpvault: MCP server for markdown vaults. GitHub. https://github.com/bitbonsai/mcpvault
Enjoyed reading this content? Let the author know!
Your likes, comments, shares, and saves help creators reach more builders.
Loading recommendations
Loading article