reprox-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@reprox-mcp Search memory for database connection details"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
reprox-mcp
reprox-mcp is a TypeScript MCP server that lets coding agents search persistent repository memory created by cliper.
Reprox reads the persistent Local JSON memory created by Cliper and exposes it to MCP clients without inventing repository facts.
Tools
Tool | Use it when | Returns |
| You need context for a question or task. | Matching memories grouped by retrieval category. |
| You need known risks or incomplete areas. | All gap summaries, high severity first. |
| You need full context for one gap. | The gap and every memory it references. |
| You need memories connected to a known memory. | Outgoing and incoming relationship neighbors. |
| You need a structural repository overview. | All architecture and repository memories. |
| You need change or release history. | Commit, release, and timeline memories, newest first. |
Related MCP server: codemem
Quickstart
Build and link or install the package, then ensure the target repository has been initialized:
cliper init
reprox mcp --path /path/to/repositoryIf repository memory is missing, the server responds with: Repository memory is not initialized; run cliper init first.
Codex configuration
Add this to ~/.codex/config.toml:
[mcp_servers.reprox]
command = "reprox"
args = ["mcp", "--path", "/absolute/path/to/repository"]Omit --path to use the server process's current working directory.
Development
npm install
npm run build
npm run pack-cleanAvailable Tools
6 toolsget_architectureA
Call when you need a broad structural overview of the repository. Returns every architecture and repository memory.
Inputs: no named parameters.
get_gapA
Call when you need the full context for one known gap. Returns that gap and every memory it explicitly references.
Inputs: id (required).
get_timelineA
Call when you need repository history, releases, or recent change context. Returns commit, release, and timeline memories ordered newest first.
Inputs: no named parameters.
list_gapsA
Call when you want to find known missing, risky, or incomplete parts of the repository. Returns all gap memories ordered by severity with their location.
Inputs: no named parameters.
search_memoryA
Call when you need repository context relevant to a question or task. Returns matching memories grouped by architecture, files, dependencies, packages, repository, commits, and gaps.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clear, distinct purpose: search for context, list/get gaps, get related memories, get architecture, and get timeline. Overlap with the generic search is acceptable because the specific getters are clearly scoped to particular memory types.
All tool names use snake_case and an imperative verb prefix like search_, list_, or get_. The only minor deviation is get_related, which uses an adjective rather than a clear noun object, but the pattern remains highly predictable.
With six tools, the server is well-scoped for a repository-context memory retrieval service. Each tool covers a meaningful access pattern without unnecessary redundancy or bloat.
The tool surface covers the full read-only retrieval lifecycle: broad search, specific gap lookup, relationship traversal, architecture overview, and timeline/history access. No significant missing operation is apparent for the stated purpose.
Maintenance
Related MCP Connectors
Hosted agent memory: store, search, and recall facts across sessions from any MCP client.
Persistent memory for AI agents to retain, retrieve, and recall conversation context through MCP.
Cross-tool persistent memory and context for AI assistants over MCP.
Team memory for AI coding agents and code reviews, reviewed by humans and served over MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI coding agents to retrieve and manage code context with hybrid search, project memory, and observability via MCP tools.30MIT
- AlicenseNot gradedqualityBmaintenanceProvides persistent, searchable memory across coding projects and machines, letting agents record and retrieve projects, reusable assets, sessions, decisions, commits, and handoffs via MCP.3Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to retrieve compact, cited repository maps through MCP tools such as search, symbol inspection, flow investigation, and deep context loading.1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceProvides coding agents with persistent repository context, including code maps, specs, timeline, team memory, and past session history, through MCP tools.Apache 2.0