hishamkaram/markdown-memory
MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API keys, no network.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~8.4k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add markdown-memory -e MARKDOWN_MEMORY_EXCLUDE=YOUR_MARKDOWN_MEMORY_EXCLUDE -- uv run markdown-memory $ npx degit hishamkaram/markdown-memory/.claude ./rig-markdown-memory # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add markdown-memory -e MARKDOWN_MEMORY_EXCLUDE=YOUR_MARKDOWN_MEMORY_EXCLUDE -- uv run markdown-memory $ npx degit hishamkaram/markdown-memory/.claude/skills/reindex-docs .claude/skills/reindex-docs $ npx degit hishamkaram/markdown-memory/.claude/skills/run-eval .claude/skills/run-eval $ npx degit hishamkaram/markdown-memory/.claude/skills/test-regression .claude/skills/test-regression
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| markdown-memory env: MARKDOWN_MEMORY_EXCLUDE | pypi | 2.5k |
Skills (3)
Similar rigs
moah0911/aftermath
—
Pragmatist 538 tok · · Q15
sloprail/sloprail
Deterministic project rules for your coding agent. They kick in when it touches a file or runs a command, and hold until met: files only where you allow, right skills loaded first, work proven by diff or logs. Not a suggestion in CLAUDE.md
Pragmatist 624 tok · · Q15
DaveGold/mcp-metadata-demo
Demo MCP server + MCP apps, and the evals that tested its metadata: what actually reaches the model, what changes answers, and a skill that applies it to new and existing servers. Companion to the paper 'The Missing Layer'. Uses Dutch open
MCP Hoarder 43.6k tok · · Q15
anomalyco/opencode
The open source coding agent.
Pragmatist 14.3k tok · · Q8