# Context Mcp Server

> MCP server exposing context tools over JSON-RPC 2.0 stdio transport

- **Type:** MCP server
- **Install:** `agentstack add mcp-contextenginehq-context-mcp-server`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [contextenginehq](https://agentstack.voostack.com/s/contextenginehq)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [contextenginehq](https://github.com/contextenginehq)
- **Source:** https://github.com/contextenginehq/context-mcp-server

## Install

```sh
agentstack add mcp-contextenginehq-context-mcp-server
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# mcp-context-server

[](https://crates.io/crates/mcp-context-server)
[](https://docs.rs/mcp-context-server)
[](LICENSE)

> `mcp-context-server` exposes a deterministic context resolution engine to AI agents via the Model Context Protocol (MCP). It enables agents to retrieve reproducible, auditably-selected context from local documentation without network dependencies.

`mcp-context-server` is the primary integration surface for agents on the Context platform.

## Architecture

The MCP server is a thin protocol adapter over the deterministic context engine.

Agent → MCP client → mcp-context-server → context-core → context cache

- `context-core` performs deterministic selection
- The server provides a stable JSON-RPC interface
- No network calls or external services are required
- Designed for on-premise and air-gapped environments

## Creating caches

Caches are created using the `context` CLI:

```bash
context build --sources ./docs --cache ./caches/my-cache
```

See the `context-cli` repository for details.

## Tools

| Tool | Description |
|------|-------------|
| `context.resolve` | Resolve context from a cache using a query and token budget |
| `context.list_caches` | List available context caches under the server's cache root |
| `context.inspect_cache` | Inspect cache metadata and validity |

## Configuration

The server is configured via environment variables:

| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| `CONTEXT_CACHE_ROOT` | yes | — | Root directory containing context caches |
| `CONTEXT_TOOL_TIMEOUT_SECS` | no | 30 | Maximum seconds per tool call |

## Running

```bash
CONTEXT_CACHE_ROOT=./caches ./dist/mcp-context-server
```

The server reads JSON-RPC requests from stdin and writes responses to stdout. It is designed to be launched by an MCP client (e.g., Claude Desktop, an agent framework).

## MCP client configuration

For Claude Desktop, add to your MCP config:

```json
{
  "mcpServers": {
    "context": {
      "command": "/path/to/mcp-context-server",
      "env": {
        "CONTEXT_CACHE_ROOT": "/path/to/your/caches"
      }
    }
  }
}
```

## Protocol

- Transport: stdio (JSON-RPC 2.0, newline-delimited)
- Protocol version: `2024-11-05`
- All responses are deterministic
- Error codes: `cache_missing`, `cache_invalid`, `invalid_query`, `invalid_budget`, `io_error`, `internal_error`

## Determinism Guarantees

For identical inputs (cache contents, query, and budget), the server guarantees:

- Byte-identical responses
- Stable document ordering
- Stable floating-point representations
- No hidden state across requests

Determinism is enforced by a compatibility test harness across versions and platforms.

## Failure Semantics

- Tool errors return structured MCP error responses
- The server never panics for user-input errors
- IO failures are reported as `io_error`
- Invalid caches are reported as `cache_invalid`

## Build

```bash
make build     # debug build
make test      # run all tests (31 tests including 11 golden snapshot tests)
make check     # cargo check + clippy
make release   # optimized build, binary copied to dist/
make clean     # remove artifacts
```

The release binary is named `mcp-context-server` and placed in `dist/`.

## Spec references

See `spec_refs.md` for links to the governing specifications.

---

"Context Engine" is a trademark of Context Engine Contributors. The software is open source under the [Apache License 2.0](LICENSE). The trademark is not licensed for use by third parties to market competing products or services without prior written permission.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [contextenginehq](https://github.com/contextenginehq)
- **Source:** [contextenginehq/context-mcp-server](https://github.com/contextenginehq/context-mcp-server)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-contextenginehq-context-mcp-server
- Seller: https://agentstack.voostack.com/s/contextenginehq
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.