Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y @sensegrep/[email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
SENSEGREP_ROOT=<value> SENSEGREP_PROVIDER=<value> GEMINI_API_KEY=<secret> claude mcp add io.github.stahldavid-sensegrep -- npx -y @sensegrep/mcp@1.5.3รันในเทอร์มินัล
{ "mcpServers": { "io.github.stahldavid-sensegrep": { "command": "npx", "args": [ "-y", "@sensegrep/[email protected]" ], "env": { "SENSEGREP_ROOT": "<value>", "SENSEGREP_PROVIDER": "<value>", "GEMINI_API_KEY": "<secret>" } } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
semantic grep for AI coding agents
sensegrep understands your code semantically. Instead of matching text patterns, it uses AI embeddings and tree-sitter AST parsing to find code by - so you can search for "authentication logic" and actually find your auth functions, even if they never contain the word "authentication".
Semantic + structural code search MCP server for AI-native development.
AI agents should not read more code, they should read the right code. sensegrep combines semantic search, exact matching, and AST-aware structural retrieval to deliver smaller, more relevant context.
For agent routing, search is the default for discovery: questions about behavior, concepts, structure, or where/how something is implemented. Use literal only for a known exact string or regex, an exhaustive occurrence audit, or verification/refinement after semantic discovery. If the intent is ambiguous, start with search.
MP4 fallback: assets/time-to-value.mp4
Watch full product demo (25s): assets/time-to-value-full.mp4
Traditional search tools (grep, ripgrep, ast-grep) match text patterns. sensegrep matches concepts:
Optional remote evaluation: Jev setup, evidence-aware reranking, group labels and duplicate judgments. It is off by default and works alongside local Ollama embeddings.
The fastest way to get sensegrep into Claude Code — zero configuration:
claude plugin marketplace add Stahldavid/sensegrep
claude plugin install sensegrep
This automatically sets up the MCP server and teaches Claude when and how to use sensegrep instead of grep. No manual JSON editing required.
Marketplace setup (required on first install):
claude plugin marketplace add Stahldavid/sensegrep claude plugin install sensegrepAfter the marketplace has been added once, the explicit marketplace form also works:
claude plugin install sensegrep@sensegrepRunning
claude plugin install sensegrep@sensegrepon a fresh machine beforeclaude plugin marketplace add Stahldavid/sensegrepwill fail because Claude Code does not know thesensegrepmarketplace yet.
npm i -g @sensegrep/cli
# Smoke-test local CLI/core/config without calling embeddings
sensegrep selftest --root .
# Default local embeddings use Ollama when no API key/provider is configured
ollama pull qwen3-embedding:0.6b
sensegrep index --root .
# Search by meaning
sensegrep search "error handling and retry logic" --type function --exported --exclude "*.md"
# Known exact text, deterministic and exhaustive: no embedding call
sensegrep literal "X-Goog-Message-Number" --include "src/**"
# Compact evidence cards, followed by deterministic expansion
sensegrep search "authentication flow" --purpose understand --json
sensegrep show <result-id> --before 10 --after 20
# Exhaustive within the ripgrep-visible filesystem, independent of the index
sensegrep literal "TODO:" --filesystem --max-output-bytes 50000 --json
# Complete changed-file review coverage in bounded batches
sensegrep audit "security regressions" --base origin/main --require-coverage --continue-uncovered --batch-tokens 4000 --max-total-tokens 8000 --max-output-bytes 32000 --max-batches 8
# Build a reading map for a broad theme
sensegrep survey "authentication login token" --language typescript --limit 4
# Break a broad topic into coherent subthemes
sensegrep cluster "checkout payment order cart" --limit 4
# Find duplicates
sensegrep detect-duplicates --threshold 0.85
sensegrep detect-duplicates --threshold 0.85 --timeout 30s --resume-cursor 0 --json
Agent-facing JSON is minified and minimal by default. Opt into --json-detail content,
--diagnostic, --json-detail full, or --pretty only when that additional payload is needed.
Schema v2 uses one card vocabulary across transports: id, file, lines, symbol,
kind, rank, and relevance. Minimal output keeps retrieval sufficiency, compact index
state, and structured warnings; budgets appear only when constrained. Physical output
budgets apply to the final serialized JSON and retain a partial evidence card when possible.
Duplicate JSON excludes source code unless --show-code is supplied. Survey and cluster
JSON default to actionable summary mode with representative IDs.
Install from the Cursor marketplace or via CLI:
cursor plugin install sensegrep
Includes the MCP server, an always-on rule to prefer sensegrep over grep, and a skill with full filter reference. Cursor plugin status: pending marketplace approval.
One-click MCP install link for Cursor:
Fallback deeplink (copy/paste if needed):
cursor://anysphere.cursor-deeplink/mcp/install?name=sensegrep&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBzZW5zZWdyZXAvbWNwQGxhdGVzdCJdfQ%3D%3D
Install from the public marketplace — no manual config:
codex plugin marketplace add Stahldavid/sensegrep
codex plugin install sensegrep
See the Codex recipe for the manual ~/.codex/config.toml setup.
npx -y @sensegrep/mcp
Add to your MCP configuration:
{
"servers": {
"sensegrep": {
"command": "npx",
"args": ["-y", "@sensegrep/mcp"]
}
}
}
Or with npm global install first:
npm install -g @sensegrep/mcp
{
"servers": {
"sensegrep": {
"command": "sensegrep-mcp"
}
}
}
The MCP server provides canonical sensegrep_search, sensegrep_show, sensegrep_literal, sensegrep_context, sensegrep_survey, sensegrep_cluster, sensegrep_graph, sensegrep_index, and sensegrep_detect_duplicates tools. Legacy dotted names such as sensegrep.search remain available as compatibility aliases where supported.
For terminal-first agents or CI, you don't need an MCP server. Install the CLI and the
sensegrep-cli Agent Skill, which teaches the agent to run
sensegrep commands directly:
npm i -g @sensegrep/cli
npx skills add Stahldavid/sensegrep --skill sensegrep-cli -g
See docs/agent-skills.md for when to use the MCP tools vs the CLI skill.
Search for "Sensegrep" in the VS Code marketplace, or install from the extension page.
Features: semantic search sidebar, duplicate detection, code lens, semantic folding, and multi-root auto-indexing/watch mode.
Copy-paste setup and practical workflows:
Full index: docs/recipes/README.md
Source Code
│
▼
┌─────────────┐ ┌──────────────┐ ┌──────────────┐
│ Tree-Sitter │───▶│ Chunker │───▶│ Embeddings │
│ AST Parser │ │ (symbols + │ │ (Ollama, │
│ │ │ metadata) │ │ Gemini, etc.)│
└─────────────┘ └──────────────┘ └──────────────┘
│
▼
┌──────────────┐
Query ──────▶│ LanceDB │
│ Vector Search│
└──────┬───────┘
│
▼
┌──────────────┐
│ Tree-Shaker │──▶ Results
│ (collapse │
│ irrelevant) │
└──────────────┘
<script> / <script setup> semantic support)sensegrep supports 30+ structural filters that can be combined with semantic search:
# Find exported async functions with high complexity
sensegrep search "data processing" --type function --exported --async --min-complexity 5
# Find Python dataclasses
sensegrep search "user model" --type class --variant dataclass --language python
# Find undocumented complex code (refactoring candidates)
sensegrep search "business logic" --min-complexity 10 --has-docs false
# Filter by decorator
sensegrep search "route handler" --type function --decorator route
# Keep docs and markdown out of results
sensegrep search "authentication flow" --include "src/**/*.ts" --exclude "*.md"
# Build a reading map for onboarding a domain
sensegrep survey "authentication login token" --language typescript --limit 4
# Split a broad backend topic into subthemes
sensegrep cluster "price list commission ncm uf packaging" --language java --include "backend-api/**/*.java"
# Build an agent context pack with a hard estimated-token budget
sensegrep context "authentication request flow" --max-tokens 8000
# Review only code changed against a Git base
sensegrep audit "security and regression risks" --base origin/main
# Navigate the local symbol graph
sensegrep references loadUser
sensegrep impact loadUser --depth 3
sensegrep trace handleRequest loadUser
Graph nodes use canonical file/range identities. Ambiguous same-name call targets are omitted instead of expanded into speculative impact edges.
# Inspect local work before any embedding request
sensegrep index --dry-run --no-watch
# Interrupted full builds resume their fingerprint-matched staging table
sensegrep index --full --no-watch
# Compare safe concurrency candidates without changing saved config
sensegrep benchmark --concurrency 1,2,4 --samples 16
# Keep independent indexes for different models/settings
sensegrep index --profile fast --no-watch
sensegrep profiles
# Keep LanceDB, graph, tools, and watcher warm behind a local HTTP endpoint
sensegrep daemon start
sensegrep daemon endpoint
sensegrep daemon call --tool search --arguments '{"query":"request routing","limit":5}'
# Agent-native planning and task-level quality evaluation
sensegrep investigate "where does payment gate room access?" --dry-run
sensegrep eval sensegrep-eval.yaml
Diagnostic commands are strictly read-only. An incompatible index reports migrationRequired: true; rebuild it with sensegrep index migrate --no-watch. Full builds stage and validate a new Lance table before switching metadata, while prior generations are retained for concurrent readers and rollback diagnostics.
Changed files reuse vectors for content-identical chunks, even when neighboring chunks or metadata changed. Full indexes checkpoint staging tables and skip IDs already persisted after a restart. For large indexes, LanceDB ANN and scalar indexes are created automatically at 10,000 chunks; set SENSEGREP_ANN_MIN_CHUNKS=0 to disable or choose another threshold.
Language support can be extended without modifying core. A plugin exports a LanguageSupport object (default, language, or languages[]) with its extensions and optional chunk(content, filePath) implementation. Add project-relative ESM modules or package names to languagePlugins in sensegrep.config.json, or set SENSEGREP_LANGUAGE_PLUGINS to a comma-separated list.
{
"languagePlugins": ["./tools/sensegrep-ruby.mjs"]
}
sensegrep supports local Ollama by default plus Gemini, OpenAI-compatible APIs, and Amazon Bedrock. If no API key or provider is configured, it defaults to Ollama at http://127.0.0.1:11434 with qwen3-embedding:0.6b (1024 dimensions, 32K context). Run sensegrep selftest --root . before indexing to confirm the selected provider/model/dimension and credential/endpoint guidance without making embedding calls.
# Default local Ollama embeddings (no API key)
ollama pull qwen3-embedding:0.6b
sensegrep search "auth flow"
# Recommended: Gemini embeddings (best quality)
export SENSEGREP_PROVIDER=gemini
export GEMINI_API_KEY="your_ai_studio_key"
sensegrep search "auth flow" --provider gemini --embed-model gemini-embedding-001
# OpenAI-compatible provider
export SENSEGREP_PROVIDER=openai
export SENSEGREP_OPENAI_API_KEY="your_api_key"
export SENSEGREP_OPENAI_BASE_URL="https://api.fireworks.ai/inference/v1"
sensegrep search "auth flow" --provider openai --embed-model fireworks/qwen3-embedding-8b
# OpenRouter + Qwen3 Embedding 8B with smaller Matryoshka vectors
export SENSEGREP_PROVIDER=openai
export SENSEGREP_OPENAI_API_KEY="your_openrouter_key"
export SENSEGREP_OPENAI_BASE_URL="https://openrouter.ai/api/v1"
export SENSEGREP_EMBED_MODEL="qwen/qwen3-embedding-8b"
export SENSEGREP_EMBED_DIM=1024
export SENSEGREP_OPENAI_BATCH_SIZE=96
# Amazon Bedrock + Cohere Embed v4
export AWS_REGION="us-east-1"
export SENSEGREP_BEDROCK_API_KEY="your_bedrock_api_key"
sensegrep search "auth flow" --provider bedrock --embed-model cohere.embed-v4:0 --embed-dim 1536
Local OpenAI-compatible embedding servers also work if they implement /v1/embeddings; set SENSEGREP_PROVIDER=openai, SENSEGREP_OPENAI_BASE_URL to the server's /v1 base URL, and SENSEGREP_EMBED_DIM to the exact returned vector dimension. For native Ollama, use SENSEGREP_PROVIDER=ollama, SENSEGREP_OLLAMA_BASE_URL if not using the default, and the exact SENSEGREP_EMBED_DIM for your Ollama model.
Global defaults via ~/.config/sensegrep/config.json:
{
"provider": "ollama",
"embedModel": "qwen3-embedding:0.6b",
"embedDim": 1024
}
Common environment variables:
SENSEGREP_PROVIDER (ollama, gemini, openai, bedrock)SENSEGREP_EMBED_MODELSENSEGREP_EMBED_DIMSENSEGREP_OLLAMA_BASE_URL (Ollama, default http://127.0.0.1:11434)GEMINI_API_KEY / GOOGLE_API_KEY (Gemini)SENSEGREP_OPENAI_API_KEY / FIREWORKS_API_KEY / OPENAI_API_KEY (OpenAI-compatible)SENSEGREP_OPENAI_BASE_URL (OpenAI-compatible, default https://api.fireworks.ai/inference/v1)SENSEGREP_OPENAI_BATCH_SIZE (OpenAI-compatible request batch size)SENSEGREP_OPENAI_CONCURRENCY / SENSEGREP_EMBED_CONCURRENCY (provider request concurrency)SENSEGREP_INDEX_EMBED_CONCURRENCY (concurrent index embedding batches)SENSEGREP_QUERY_CACHE (true by default; set false for controlled benchmarks or sensitive environments)SENSEGREP_QUERY_CACHE_TTL_MS / SENSEGREP_QUERY_CACHE_MAX_ENTRIES (persistent query-vector cache bounds)SENSEGREP_ADAPTIVE_HYBRID_DELAY_MS / SENSEGREP_ADAPTIVE_HYBRID_MIN_SCORE (adaptive hybrid tuning)SENSEGREP_ANN_MIN_CHUNKS (automatic ANN threshold; 0 disables)SENSEGREP_PROFILE (named side-by-side index profile)SENSEGREP_LANGUAGE_PLUGINS (comma-separated ESM language plugins)SENSEGREP_OPENROUTER_REFERER / SENSEGREP_OPENROUTER_TITLE (optional OpenRouter attribution headers)SENSEGREP_BEDROCK_API_KEY (Amazon Bedrock bearer API key; omit when using the AWS SDK credential chain)SENSEGREP_BEDROCK_REGION / AWS_REGION / AWS_DEFAULT_REGION (Amazon Bedrock)SENSEGREP_ROOT (MCP root directory)SENSEGREP_WATCH (MCP watcher toggle)For the complete and official runtime variable list, see docs/mcp-setup.md.
OpenRouter Qwen embeddings use one provider request at a time by default. Benchmarking on
high-latency endpoints commonly shows that additional concurrent requests reduce throughput;
use sensegrep benchmark --concurrency 1,2,4 --samples 256 --json before overriding the default.
The benchmark varies concurrency only for the OpenAI-compatible adapter, and only
when samples span multiple HTTP batches. Native Ollama, Gemini, and Bedrock report
a sequential baseline with recommendedConcurrency: null and no environment
recommendation. This does not tune index workers or Ollama server slots.
Index plans report internal estimatedBatches separately from estimatedRequests;
for Ollama, HTTP requests use httpBatchSize (default 16), including splits inside
each index batch. Request estimates exclude retries; dry runs do not subtract
vectors that will be reused. Other providers retain approximate request estimates.
Search preserves diverse file anchors while admitting complementary symbols and bounded local helper expansion. context defaults to 12,000 estimated output tokens; use 4,000 for a compact pack or 8,000 for broader investigation. Explicit file/token limits remain respected. Weak-evidence warnings are advisory, not proof that code is absent. See search quality and budgets for behavior, limitations, and a reproducible comparison script.
Each index records the embedding provider, model, dimension, distance metric, and a non-secret endpoint/configuration fingerprint. If you change provider, model, base URL, dimension, local server pooling behavior, or task-prefix strategy, rebuild the index with sensegrep index --root . --full --no-watch. Same dimension does not make embeddings interchangeable; two 768-dimensional models still produce different vector spaces.
More embedding providers and API integrations may be added in the future.
Reproducible qualitative examples from public repositories:
ripgrep / ast-grep is scheduled for Month 2.See the architecture guide for runtime and persistence design, and CONTRIBUTING.md for development setup and contribution guidelines. The VS Code extension stores provider API keys in VS Code SecretStorage; workspace settings contain only non-secret configuration.
See Token-aware chunking and local Ollama for the 8K runtime window, configurable symbol/target/maximum budgets, local tokenizer counting, token-bounded HTTP batches, and safe index migration. context --max-tokens controls output independently.
Semantic + structural code search MCP server for AI-native development.
{ "mcpServers": { "io.github.stahldavid-sensegrep": { "command": "npx", "args": [ "-y", "@sensegrep/[email protected]" ], "env": { "SENSEGREP_ROOT": "<value>", "SENSEGREP_PROVIDER": "<value>", "GEMINI_API_KEY": "<secret>" } } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ผู้เผยแพร่ระบุตัวแปรสภาพแวดล้อมเหล่านี้: SENSEGREP_ROOT, SENSEGREP_PROVIDER, GEMINI_API_KEY
Sensegrep ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-09 Semantic + structural code search MCP server for AI-native development.