Code Intel vs Graft
A side-by-side look at the Code Intel and Graft MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Code Intel for coding agents work as a local process; choose Graft 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 Code Intel 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
get_task_context, search_symbol, search_codebase.
Choose Graft 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 have the keys it needs:
GRAFT_ROOT_PATH. - You want tools like
safe_read, graft_edit, file_outline.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Coding Agents | Coding Agents |
| Quality signal | 59/100 · Good | 65/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | None listed | GRAFT_ROOT_PATH |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 17 |
| Directory activity | 0 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 5 | 34 |
| Full listing | View Code Intel | View Graft |
Tools & capabilities
Code Intel tools 5
get_task_contextFirst call for any new or broad task, with the whole request: code for every part of it within a token budget. The reply says which parts are covered, whether it is `complete`, and lists at most three exact `Next` calls if not (`mode`: `minimal`, `normal`, `deep`)search_symbolA known function, class, or type namesearch_codebaseConceptual search with an optional `max_tokens` capfind_referencesWhere an identifier appears (textual, not compiler-resolved)get_file_contextExact current source read from disk; batch several `ranges` such as `"src/a.ts:120-168"` in one call
Graft tools 34
safe_readPolicy-enforced file read. Returns full content for small files, structural outline with jump table for large files, or refusal with reason code for banned files. Detects re-reads and returns cached outlines or structural diffs.graft_editPerform one governed exact string replacement in a repo file. Requires path, old_string, and new_string. Refuses missing or ambiguous old_string matches and policy-denied paths.file_outlineStructural skeleton of a file — function signatures, class shapes, exports. Includes a jump table mapping each symbol to its line range for targeted read_range follow-ups.read_rangeRead a bounded range of lines from a file. Maximum 250 lines. Use jump table entries from file_outline or safe_read to target specific symbols.changed_sinceCheck if a file changed since it was last read. Returns structural diff (added/removed/changed symbols) or 'unchanged'. Peek mode by default; pass consume: true to update the observation cache.graft_diffStructural diff between two git refs. Shows added, removed, and changed symbols per file — not line hunks. Defaults to working tree vs HEAD.run_captureExecute a shell command and return the last N lines of output (default 60). Responses include an explicit policy boundary. Persisted logs can be disabled and obvious secrets are redacted before writing to .graft/logs/capture.log.state_saveSave session working state (max 8 KB). Use for session bookmarks: current task, files modified, next planned actions.state_loadLoad previously saved session state. Returns null if no state has been saved.doctorRuntime health check. Shows project root, parser status, active thresholds, session depth, message count, and burden summary.activity_viewInspect recent bounded local artifact history for the active workspace, anchored to the current commit when possible.causal_statusInspect the active causal workspace and persisted local-history posture.- +22 more on the listing page
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.
Code Intel
{
"mcpServers": {
"pranitmodi-code-intel": {
"command": "npx",
"args": [
"-y",
"@pranitmodi/code-intel"
]
}
}
}
Graft
{
"mcpServers": {
"flyingrobots-graft": {
"command": "npx",
"args": [
"-y",
"@flyingrobots/graft"
],
"env": {
"GRAFT_ROOT_PATH": "YOUR_GRAFT_ROOT_PATH_HERE"
}
}
}
}
Frequently asked questions
Code Intel is categorized under Coding Agents and uses a local stdio subprocess. Graft belongs to Coding Agents and uses a local stdio subprocess. Pick Code Intel for coding agents work and Graft 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.
Code Intel is listed as free. Auth: no auth required. Graft 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 pranitmodi-code-intel and flyingrobots-graft as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Code Intel has a quality signal of 59/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Graft has 65/100 (Great) with 1 views, 0 installs and 17 GitHub stars.