Context-Engine MCP - Agentic Context Compression Suite
> /plugin marketplace add Context-Engine-AI/Context-Engine> /plugin install context-engine@context-engine-skills
What's inside
Context Engine ships AI agent skills that teach your coding assistant how to use 30+ MCP tools for semantic search, symbol graph navigation, memory, and more.
Recommended: Install natively from the public GitHub repo:
# Add the marketplace (one-time)
/plugin marketplace add Context-Engine-AI/Context-Engine
# Install the skill
/plugin install context-engine
This pulls the skill directly from GitHub and auto-loads MCP tool guidance into your session.
Alternatively, copy the rules file manually:
cp -r skills/context-engine/ your-project/.claude/
Context Engine rules are included in .cursorrules at the root of your workspace. Cursor picks this up automatically when the file is present.
# Copy to your project root
cp .cursorrules your-project/.cursorrules
Recommended: Install natively using the built-in skill installer โ just ask Codex:
"Install the context-engine skill from https://github.com/Context-Engine-AI/Context-Engine"
Codex will pull .codex/skills/context-engine/ (including SKILL.md and reference docs) into ~/.codex/skills/ automatically.
Or install manually:
cp -r .codex/skills/context-engine/ ~/.codex/skills/context-engine/
cp -r .codex/skills/ your-project/.codex/skills/
cp -r .augment/ your-project/.augment/
cp GEMINI.md your-project/GEMINI.md
The core skill file works with any AI assistant that supports custom instructions:
cp skills/context-engine/SKILL.md your-project/
Then tell your assistant: "Read SKILL.md for instructions on using Context Engine MCP tools."
If you use Claude Code, Codex, or another terminal-based MCP client, install the MCP bridge to connect your codebase to Context Engine without VS Code:
npm install -g @context-engine-bridge/context-engine-mcp-bridge
# Authenticate, index your codebase, and start watching for changes
ctxce connect <your-api-key> --workspace /path/to/repo
# Run as a background daemon (recommended)
ctxce connect <your-api-key> --workspace /path/to/repo --daemon
ctxce status # Check if the daemon is running
ctxce stop # Stop the background daemon
| Flag | Alias | Description |
|---|---|---|
--workspace <path> | -w | Workspace root (default: cwd) |
--daemon | -d, --bg | Run as background daemon |
--interval <sec> | File watch interval in seconds (default: 30) | |
--no-watch | --once | Index once, don't watch for changes |
--skip-index | --auth-only | Authenticate only, skip initial index |
Once connected, point your MCP client at the bridge:
# stdio mode (for Claude Code, Codex, etc.)
ctxce mcp-serve --workspace /path/to/repo
# HTTP mode (for clients that speak HTTP)
ctxce mcp-http-serve --workspace /path/to/repo --port 30810
The daemon and MCP server share auth via ~/.ctxce/auth.json. Logs are at ~/.context-engine/daemon.log.
For full bridge documentation, see Context-Engine-MCP-Bridge.
The skills teach your AI assistant to:
search as the default tool โ auto-routes queries to the best backend (semantic search, Q&A, symbol graph, tests, config)symbol_graph โ find callers, callees, definitions, importers, subclassesbatch_search, batch_symbol_graph, batch_graph_query for 75%+ token savingsmemory_store and memory_find for persistent context across sessionscross_repo_search with boundary tracing for multi-repo codebasespattern_search for retry loops, error handling, singletons across languagessearch_commits_for and change_history_for_pathSee skills/context-engine/SKILL.md for the complete tool reference.
npm i -g @context-engine-bridge/context-engine-mcp-bridge && ctxce connect <api-key> --daemonยฉ 2025 Context Engine Inc. and John Donalson.
.augment/
rules/
context-engine.md
.claude-plugin/
marketplace.json
.codebase/
.gitkeep
.codex/
config.toml
skills/
context-engine/
references/
patterns.md
tool-reference.md
SKILL.md
.cursorrules
.dockerignore
.DS_Store
.env
.env.example
.github/
workflows/
ci.yml
claude.yaml
deploy.yml
publish-cli.yml
.gitignore
.indexignore
.npmrc
.prettierignore
.prettierrc
.qdrantignore
.skills/
mcp-tool-selection/
SKILL.md
.vscode/
settings.json
AUTHORS
bench/
clone_snapshot.py
configs/
ctx_ab_configs.json
copy-coll.py
datasets/
public_v1.json
doc.md
eval_quality.py
eval.py
gold/
public_v1.queries.jsonl
queries.txt
README.md
run_matrix.py
build-images.sh
CODEOWNERS
config/
clickhouse-config.xml
docker_related_config.xml
otel-collector-config.yaml
ctx_config.example.json
ctx-hook-simple.sh
ctx-mcp-bridge/
.gitignore
bin/
ctxce.js
docs/
debugging.md
package-lock.json
package.json
publish.sh
README.md
src/
authCli.js
authConfig.js
cli.js
mcpServer.js
oauthHandler.js
resultPathMapping.js
deploy/
kubernetes/
cleanup.sh
code-models-pvc.yaml
configmap.yaml
deploy.sh
hpa.yaml
indexer-services.yaml
ingress.yaml
kustomization.yaml
learning-reranker-worker.yaml
llamacpp.yaml
Makefile
mcp-http.yaml
mcp-indexer.yaml
mcp-memory.yaml
namespace.yaml
networkpolicy.yaml
qdrant.yaml
rbac.yaml
README.md
upload-codebase-pvc.yaml
upload-pvc.yaml
upload-service.yaml
nginx/
context-engine-rmcp.conf
dev-workspace/
.gitkeep
docker-compose-bindmount-checkout.yml
docker-compose.openlit.yml
docker-compose.yml
Dockerfile
Dockerfile.indexer
Dockerfile.llamacpp
Dockerfile.mcp
Dockerfile.mcp-indexer
Dockerfile.upload-service
docs/
ARCHITECTURE.md
BENCHMARKS.md
CLAUDE.example.md
commit-indexing/
cmds.md
experiments.md
overview.md
CONFIG_DRIFT.md
CONFIGURATION.md
ctx/
CTX_CLI.md
claude-hook-example.json
DEVELOPMENT.md
GETTING_STARTED.md
IDE_CLIENTS.md
MCP_API.md
MEMORY_GUIDE.md
MULTI_REPO_COLLECTIONS.md
OBSERVABILITY.md
TROUBLESHOOTING.md
vscode-extension.md
e2e/
demo.test.ts
enhance1.png
eslint.config.js
GEMINI.md
LICENSE
llm.png
Makefile
mcp-proxy/
mcp-indexer-proxy.py
models/
model_qint8_avx512_vnni.onnx
tokenizer.json
NOTICE
package-lock.json
package.json
playwright.config.ts
pytest.ini
README.md
requirements.txt
scripts/
__init__.py
add_vector_name.py
admin_ui.py
ast_analyzer.py
async_subprocess_manager.py
auth_backend.py
benchmarks/
__init__.py
auto_tuner.py
coir/
__init__.py
indexer.py
retriever.py
run_ablation.sh
runner.py
common.py
core_indexer.py
cosqa/
__init__.py
dataset.py
indexer.py
pca_init.py
run_ablation.sh
runner.py
efficiency_benchmark.py
eval_harness.py
expand_bench.py
experiment.py
grounding_scorer.py
qdrant_utils.py
recommendations.py
refrag_bench.py
router_bench.py
rrf_quality.py
run_all.py
swe/
__init__.py
dataset.py
repo_manager.py
runner.py
test_env_snapshot.py
trace_optimizer.py
trm_bench.py
tunable_config.py
validation_loop.py
cache_manager.py
collection_admin.py
collection_health.py
create_indexes.py
ctx.py
deduplication.py
dev_up.sh
dev-setup.sh
embedder.py
gpu_toggle.sh
health_check.py
hybrid/
hybrid_config.py
hybrid_embed.py
hybrid_expand.py
hybrid_filters.py
hybrid_qdrant.py
hybrid_ranking.py
hybrid_search.py
__init__.py
config.py
embed.py
expand.py
filters.py
qdrant.py
ranking.py
indexing_admin.py
ingest/
ingest_code.py
ingest_history.py
__init__.py
chunking.py
cli.py
config.py
exclusions.py
metadata.py
pipeline.py
pseudo.py
qdrant.py
symbols.py
tree_sitter.py
vectors.py
k8s_uploader.py
learning_reranker_worker.py
llm_utils.py
logger.py
mcp_admin_tools.py
mcp_auth.py
mcp_code_signals.py
mcp_context_answer.py
mcp_impl/
__init__.py
admin_tools.py
code_signals.py
context_answer.py
context_search.py
info_request.py
memory.py
pattern_search.py
query_expand.py
search_history.py
search_specialized.py
search.py
symbol_graph.py
toon.py
utils.py
workspace.py
mcp_indexer_server.py
mcp_memory_server.py
mcp_router/
mcp_router.py
__init__.py
__main__.py
batching.py
cli.py
client.py
config.py
hints.py
intent.py
memory.py
planning.py
scratchpad.py
validation.py
mcp_toon.py
mcp_utils.py
mcp_workspace.py
memory_backup.py
memory_restore.py
openlit_init.py
pattern_detection/
__init__.py
catalog.py
encoder.py
extractor.py
prune.py
search.py
progressive_train.py
prune.py
qdrant_client_manager.py
quantize_reranker.py
query_named_vector.py
query_optimizer.py
refrag_glm.py
refrag_llamacpp.py
refrag_minimax.py
refrag_openai.py
refrag_phi.py
remote_upload_client.py
rerank_ab_test.py
rerank_eval.py
rerank_events.py
rerank_local.py
rerank_query.py
rerank_real_benchmark.py
rerank_recursive/
rerank_recursive.py
__init__.py
alpha_scheduler.py
confidence.py
expander.py
hybrid_weights.py
projection.py
recursive.py
refiner.py
scorer.py
state.py
utils.py
vicreg.py
rerank_tools/
__init__.py
ab_test.py
benchmark.py
eval.py
events.py
local.py
query.py
train.py
rerank_train.py
reranker.py
router_eval.py
semantic_expansion.py
setup_reranker.py
smoke_test.py
standalone_upload_client.py
subprocess_manager.py
sync_env_to_k8s.py
toon_encoder.py
upload_auth_utils.py
upload_delta_bundle.py
upload_service.py
utils.py
wait-for-qdrant.sh
warm_all_collections.py
warm_start.py
watch_index_core/
__init__.py
config.py
handler.py
processor.py
pseudo.py
queue.py
rename.py
routing.py
utils.py
watch_index.py
workspace_state.py
skills/
context-engine/
SKILL.md
src/
app.d.ts
app.html
app.scss
lib/
images/
github.svg
svelte-logo.svg
svelte-welcome.png
svelte-welcome.webp
routes/
+layout.svelte
+page.server.ts
+page.svelte
+page.ts
$types.ts
contact/
+page.svelte
Counter.svelte
docs/
[slug]/
+page.server.ts
+page.svelte
+page.ts
+layout.svelte
Header.svelte
layout.css
static/
... 102 moreFAQ
context-engine is a Claude Code plugin with 1 hand-picked skill for development work, indexed on Flowy. Install it with the command on its page. It includes context-engine. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.