ArcAgent MCP vs Context Mode
A side-by-side look at the ArcAgent MCP and Context Mode MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose ArcAgent MCP for coding agents work as a local process; choose Context Mode for coding agents as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose ArcAgent MCP when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
ARCAGENT_API_KEY.
Choose Context Mode when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
ctx_batch_execute, ctx_execute, ctx_execute_file.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Coding Agents | Coding Agents |
| Quality signal | 40/100 · Fair | 69/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | ARCAGENT_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 2 | 32,005 |
| Directory activity | 2 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | Not listed | 10 |
| Full listing | View ArcAgent MCP | View Context Mode |
Tools & capabilities
ArcAgent MCP tools
No tool names declared yet. Check the project README from the listing page.
Context Mode tools 10
ctx_batch_executeRun multiple commands + search multiple queries in ONE call. Opt-in `concurrency: 1-8` for I/O-bound batches.ctx_executeRun code in 12 languages. Only stdout enters context.ctx_execute_fileProcess files in sandbox. Raw content never leaves.ctx_indexChunk markdown into FTS5 with BM25 ranking.ctx_searchQuery indexed content with multiple queries in one call.ctx_fetch_and_indexFetch URL, chunk and index. Cache reuses content within TTL (default 24h, override per-call with `ttl: <ms>`). `ttl: 0` or `force: true` to bypass. Pass `requests: [{url, source}, ...]` + `concurrency: 1-8` for parallel multi-URL.ctx_statsShow context savings, call counts, and session statistics.ctx_doctorDiagnose installation: runtimes, hooks, FTS5, versions.ctx_upgradeUpgrade to latest version from GitHub, rebuild, reconfigure hooks.ctx_purgePermanently deletes all indexed content from the knowledge base.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
ArcAgent MCP
{
"mcpServers": {
"arcagent-mcp": {
"command": "npx",
"args": [
"-y",
"arcagent-mcp"
],
"env": {
"ARCAGENT_API_KEY": "YOUR_ARCAGENT_API_KEY_HERE"
}
}
}
}
Context Mode
{
"mcpServers": {
"context-mode": {
"command": "npx",
"args": [
"-y",
"context-mode"
]
}
}
}
Frequently asked questions
ArcAgent MCP is categorized under Coding Agents and uses a local stdio subprocess. Context Mode belongs to Coding Agents and uses a local stdio subprocess. Pick ArcAgent MCP for coding agents work and Context Mode for coding agents.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
ArcAgent MCP has no declared pricing — check the project's own site. Context Mode is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add arcagent-mcp and context-mode as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, ArcAgent MCP has a quality signal of 40/100 (Fair) with 2 views, 0 installs and 2 GitHub stars. Context Mode has 69/100 (Great) with 2 views, 0 installs and 32,005 GitHub stars.