Project RAG wiki
Allows agents to search, read, list, and write Markdown wiki notes indexed with vector embeddings, supporting frontmatter and semantic sections for structured knowledge retrieval.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
local-rag-wiki
A repo-local RAG wiki for AI agents: a per-repository MCP knowledge service (governed search / read / write of Markdown wiki notes) plus an installer that wires it into your agent tooling. Docker is required to run the service.
Install
Run in your repository root with Docker running:
npx github:ihorleleka/Local-Rag-Wiki install .Besides the files below, install and update set up the service: they pull the
pinned image, stop a repository container that still runs an older image, remove
the superseded image tag (kept if another repository's container still uses it),
and start the container so the one-time embedding-model download (~80 MB) happens
here instead of during your first agent launch. If Docker is unavailable the files
are still installed and a warning tells you to run wiki-kit pull . and
wiki-kit start . later; --skip-docker (or WIKI_KIT_SKIP_DOCKER=1) skips this
step.
This scaffolds the managed .agents/ runner, the AGENTS.md policy section,
DSH workspace assets (.dsh/mcp.servers.yml and its scoped MCP bridge), Claude
Code, Codex, VS Code, and OpenCode, plus a wiki/ folder. The DSH bridge stays
under .dsh/; it is never installed as a repository-root
.dsh-mcp-client.js. These integrations are additive. The MCP service starts
per repository and keeps running independently of agent clients.
Related MCP server: hw_rag_mcp
Claude Code
The installer delivers Claude Code's project-native integration surfaces:
Root
.mcp.jsondefineswiki-managerundermcpServers, pointing to the managed Node runner. Existing unrelated MCP servers are preserved..claude/skills/wiki/SKILL.mdand its authoring reference are materialized from the shared.agents/skills/wikisource. Use/wikiin Claude Code ($wikiis the invocation used by other clients). Updates refresh this managed skill even without--force, while preserving other skill directories.CLAUDE.mdreceives a bounded, managed section containing only an@AGENTS.mdimport, so Claude Code reads the same wiki policy and engineering baseline as other clients; existing project instructions outside that section are preserved.
The installer does not add MCP definitions to .claude/settings.local.json.
Older installations may still contain an obsolete mcpServers.wiki-manager
entry there; updates leave that file, user hooks, permissions, and other local
preferences untouched. Review/remove that obsolete entry yourself if desired.
No server approval or tool permission is granted automatically: accept the
workspace/project MCP trust prompts as appropriate, then check /mcp and confirm
/wiki is listed in a fresh Claude session. Docker must be available for MCP
startup. --skip-root omits all these Claude integration surfaces.
Claude Code waits 30 seconds for an MCP server to start by default
(MCP_TIMEOUT). The service binds its MCP port first and builds the index in the
background, so wiki-manager connects and lists its tools within a few seconds
even on a cold start; tool calls wait for the index only when they need it. A
start that also has to pull the image or wait for Docker Desktop can still take
longer: the runner allows up to 120 seconds. If wiki-manager fails on that
launch, run wiki-kit start . once, or start Claude Code with
MCP_TIMEOUT=150000. Claude
Code only reads .mcp.json from the
folder it is started in: open the repository root, not a parent folder that
contains several repositories, or the wiki_* tools will be missing (the /wiki
skill still works from local files).
If you move or re-clone a repository, the container name changes with the path.
The runner replaces a container whose wiki mount points elsewhere, but a container
from the old path keeps running; remove it with docker rm -f <name> (see
docker ps) and drop its volume with docker volume rm <name>-kb-data.
The .agents/plugins/marketplace.json catalog is for other agent tooling, not a
Claude Code marketplace. This integration uses project skills and project MCP
configuration directly; no Claude plugin installation is required.
Compatibility was checked against the live official documentation on 2026-11-17, not a version-pinned historical snapshot: skills and discovery, project MCP configuration and trust, settings scope, and Claude plugin marketplaces.
DeepSeek Harness
The native bundle supports DSH >=0.2.1-rc.5 <0.3.0-0. A DSH 0.3.0
prerelease or later requires a compatible wiki-kit release.
Install the native DSH bundle once into the profile you use (usually web):
dsh plugin --profile web add github:ihorleleka/Local-Rag-WikiRestart that DSH profile, open an installed repository as its workspace, and
start a session. Opening the session alone does not start the wiki bridge. When
the first direct user prompt is submitted, the bundle compares the wiki-kit
package version of the installed profile plugin—not the DSH runtime version—with
the workspace install marker. When the plugin version is newer, it runs the
workspace's .agents/update-wiki-kit.cmd on Windows or
.agents/update-wiki-kit.sh on macOS/Linux once; the updated marker prevents
another run for that plugin version. It then reads the active workspace's
.dsh/mcp.servers.yml, validates its wiki-manager entry against the managed
install marker, resolves the configured node executable through DSH's
subprocess service, and mounts the bridge through agent.ctx. It never uses
process.execPath, because that is the Electron executable in DSH Desktop.
When Docker is reachable, initial discovery finishes before the model request is
assembled, exposing stable native mcp__wiki-manager__* tools on that agent's
tool scope. If Docker Desktop is still starting, the session remains usable and
the bridge retries in the background until it can register those tools.
Identical namespaces can coexist in different agent scopes without leaking tools
between sessions.
The scoped bridge source is delivered as .dsh/.dsh-mcp-client.js (never at
repository root) and follows DSH's MCP transport, reconnect, tool-schema, and
execution pipeline. The canonical config path is .dsh/mcp.servers.yml; a
legacy dsh/mcp.servers.yml is accepted only when the canonical file is absent.
DSH core does not auto-load this file—the trusted profile bundle is its loader.
Do not add a second global MCP client for the same server.
Wiki recall is context-bounded. Prefix a prompt with $wiki to opt in
unconditionally, for example $wiki explain the deployment architecture.
Otherwise, the first direct prompt performs one L0 candidate search and injects
only individually qualifying results: relevance_score >= 0.5, direct lexical
grounding to the prompt (two shared meaningful terms or one shared identifier),
and explicit trust signals: active status, complete schema, current freshness,
present evidence, and no required verification. Pending, historical, and unknown-
trust results are excluded from automatic injection. Older service images without
these trust fields also cause automatic recall to abstain; explicit retrieval
remains available. These signals describe the indexed snapshot, not proof of live
behavior. The score is a ranking signal, not a calibrated probability; $wiki
bypasses this automatic-abstention policy for deliberate inspection. Candidate and injected L0 results use
three matches and are capped at 900
characters—about 225 tokens by the recorded estimate. It never automatically
preloads L1 packets; additional detail is a
model-directed wiki_search or wiki_read decision. Recall is cached and
in-flight deduplicated per workspace. It is turn-scoped: when the turn stops,
the evidence is replaced by an empty, non-model-visible surface event, so it
cannot accumulate in later model requests. Recall diagnostics track skipped
ordinary prompts, explicit requests, cache hits, context characters, estimated
injected tokens, and budget truncations.
The governed wiki and its MCP search are the only DSH memory path; the bundle
does not capture local prompt history. Claude Code connects to the same runner
through its MCP configuration without repository prompt-history hooks. See
.dsh/README.md for the workspace boundary.
Update
After install, refresh the managed files and the service from inside the repo — no npx needed. This also pulls the pinned image, replaces an outdated container, and starts it (see Install):
.agents\update-wiki-kit.cmd --forcesh .agents/update-wiki-kit.sh --forceLifecycle
npx github:ihorleleka/Local-Rag-Wiki status .
npx github:ihorleleka/Local-Rag-Wiki restart .
npx github:ihorleleka/Local-Rag-Wiki doctor . --livestart ., stop ., and pull . are available the same way. The repository
container persists independently of individual agent clients.
Long-running MCP sessions
The HTTP backend can expire idle MCP sessions while remaining healthy. The managed stdio runner renews a missing session on HTTP 404, then retries the rejected request once without restarting MCP or the container. Other HTTP and transport failures return errors with the caller's request ID instead of leaving calls pending. A 30-second wall-clock HTTP deadline also bounds stalled SSE responses, even when keepalive traffic continues. Network failures and timeouts are not automatically retried: a write may already have executed.
For an older installed runner, update the managed workspace files and reconnect its MCP client once to load the fix. A container/image replacement is not required for this runner-only fix.
Crash-dump protection
Starting with 0.2.5, the Linux backend disables process core dumps before loading native dependencies,
including when WSL uses a piped crash collector (where ulimit core=0 alone is
not sufficient). Managed containers additionally use --ulimit core=0:0.
The backend refuses to start on Linux if process-level protection cannot be
established. Ordinary debugger/ptrace attachment to that process is also disabled.
This contains crash-dump disk growth; it does not fix native crashes or limit RAM.
To apply this protection to an existing installation, update the managed files,
then run pull . and restart . using the lifecycle commands above. Updating
files alone does not replace a running container. Restart briefly interrupts all
clients sharing that repository's container, but retains wiki/index/model volumes.
If KB_IMAGE is overridden, use an image containing this fix; the default image
is pinned to the shared release version. Existing Windows dump files are not
removed, and no host-wide WSL settings are modified. Custom image commands that
bypass python -m kb_service also bypass its process-level protection.
How it works
This package is the installer: it scaffolds and maintains the
.agents/runner and MCP configuration in a consumer repository.kb-service/ is the Dockerized MCP knowledge service the runner launches per repository. It serves
wiki_search,wiki_read,wiki_list,wiki_tree,wiki_schema_report,wiki_edit,wiki_write,wiki_capture,wiki_delete, andwiki_renameoverPOST /mcp/(loopback by default), with atomic note persistence and targeted reindexing. Preferwiki_editfor small updates; usewiki_writefor creation or full replacements.wiki_searchsupports tiered retrieval (depth=abstract|packet) pluspath_prefixdirectory scoping.
wiki_edit(path: str, old_text: str, new_text: str) replaces exactly one literal
match in an existing note. old_text must be nonempty; empty new_text deletes
that match. It performs no write on conflicts: not_found (missing note),
text_not_found (no match), or ambiguous_match (multiple matches). See the
service write contract for details.
Agentic memory design review
See the dated comparison and delivery audit
against Mem0, Letta, Graphiti, Cognee, and OpenViking, including adopted patterns,
licensing caveats, and prioritized remaining work. The design keeps governed
Markdown and bounded retrieval rather than adding a conversation archive or graph
service. MCP availability and native skill discovery are separate capabilities;
the delivered policy names the skill file for clients without $wiki discovery.
Versioning
The installer and kb-service ride the same Git tag (X.Y.Z or vX.Y.Z).
Release automation:
Development and verification
From a clean checkout, install the locked JavaScript dependencies before running installer and scoped DSH bridge regressions:
npm ci
npm testThe dependency-free Python suite fakes native libraries and model providers; it requires Python 3.11+ and does not start Docker or download models:
python -m unittest discover -s kb-service/tests -p 'test_*.py'CI runs this suite on Python 3.11 and 3.14. See the
service verification notes for the separate
real-dependency integration suite. npm run verify:runner requires Docker and
exercises container lifecycle operations; it is not part of the offline suite.
When updating DSH-related libraries, check the supported runtime's peer ranges,
not only npm's latest tag. DSH 0.2.1-rc.5 requires Cordis ~4.0.5 and uses
Schemastery ~3.18.5; upgrading the top-level copies independently can split the
plugin dependency graph. Preserve the supported runtime baseline and verify the
scoped bridge before accepting such updates.
License
MIT (see kb-service/LICENSE).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Remote ChromaDB vector database MCP server with streamable HTTP transport
MCP server for querying Forkast documentation
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables saving, retrieving, and managing research content using ChromaDB vector storage and semantic search.5MIT
- FlicenseNot gradedqualityDmaintenanceMCP server that indexes a knowledge base into Chroma and provides search tools for retrieving document fragments via vector embeddings.-
- AlicenseNot gradedqualityCmaintenanceMCP server to query a Git-hosted Wiki, offering tools to list, search, and read Markdown documents via Codex or VS Code.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that indexes Markdown files into a local SQLite vector store and provides semantic search tools for Claude Code.5MIT