mcp vs llama_index
mcp and llama_index share 22 technologies: psycopg, pymongo, pyarrow, pyiceberg, ibm-db, oracledb, starlette, OpenAI, MCP, bedrock-agentcore, jinja2, beautifulsoup4, defusedxml, lxml, markdownify, markitdown, pdf2image, pdfplumber, Pydantic, python-json-logger, boto3, and psutil. Both are written in Python.
What they share and what sets them apart
awslabs
mcp
Open source MCP Servers for AWS
Python9.9kRead on November 14, 2026, at commit 5d58a6aWhat is mcp built with?Only in mcp
- cassandra-driver
- valkey-glide
- Postgres
- MongoDB
- asyncmy
daft
pika
- pymssql
- InfluxDB
- FastAPI
fastmcp
uvicorn
sqlglot
authlib
- bcrypt
- langdetect
- python-frontmatter
- readabilipy
ruamel-yaml
- openapi-spec-validator
prance
- coloredlogs
- docker
loguru
- botocore
kubernetes
In common
run-llama
llama_index
LlamaIndex is the document processing platform for AI
Python52.9kRead on November 13, 2026, at commit baeabbfWhat is llama_index built with?Only in llama_index
- aiomysql
- aiosqlite
- async-lru
- asyncpg
- azure-cosmos
- azure-data-tables
- azure-search-documents
- azure-storage-blob
- nebula3-python
- oss2
pgml
- pgvecto-rs
pgvector
pickleshare
psycopg2-binary
pyathena
- pydrive
- pylance
python-arango
pyvespa
- pyzmq
- Redis
snowflake-sqlalchemy
- tantivy
weaviate-client
- Neo4j
- aioboto3
lancedb
- DuckDB
- pymilvus
- pysolr
- SQLite
- tablestore
- aperturedb
- astrapy
chromadb
- dashvector
falkordb
- jaguardb-http-client
- MySQL
pinecone
clickhouse-connect
- couchdb3
- gcsfs
opendal
opengauss-sqlalchemy
- pyairtable
pymochow
- pymysql
- pyobvector
- s3fs
singlestoredb
- tcvectordb
typesense
- ElevenLabs
- anyio
- graphql-core
- jupyter-core
jupyterlab-server
tornado
- AIOHTTP
- Ray
jupyterlab-pygments
- soupsieve
- tinycss2
- ipywidgets
- jupyter-server-terminals
- jupyterlab-widgets
- matplotlib-inline
prompt-toolkit
- widgetsnbextension
matplotlib
- Rich
- SQLAlchemy
- argon2-cffi
- argon2-cffi-bindings
- azure-identity
google-auth-httplib2
google-auth-oauthlib
- cryptography
- pyjwt
- msal
- argilla
- azure-ai-agents
- azure-ai-inference
- azure-ai-projects
contextual-client
- diff-cover
- einops
firecrawl-py
friendli-client
- guardrails-ai
llama-cpp-python
llama-index-core
- llama-index-embeddings-dashscope
- llama-index-embeddings-huggingface
- llama-index-embeddings-openai
- llama-index-llms-anthropic
- llama-index-llms-azure-openai
- llama-index-llms-huggingface
- llama-index-llms-llama-cpp
- llama-index-llms-openai
- llama-index-llms-openai-like
- llama-index-node-parser-dashscope
- llama-index-program-guidance
- llama-index-readers-dashscope
- llama-index-readers-database
- llama-index-readers-remote
- llama-index-readers-upstage
- llama-index-readers-web
- llama-index-response-synthesizers-google
- llama-index-utils-azure
- llama-index-utils-huggingface
- llama-index-utils-qianfan
- llama-index-vector-stores-google
- llama-index-workflows
- mem0ai
- ms-swift
- open-clip-torch
opencv-python
- openinference-instrumentation-llama-index
- openvino-tokenizers
- PaddlePaddle
portkey-ai
- reka-api
- tavily-python
- typecast-python
- torch
llama-index-instrumentation
- transformers
- ibm-watsonx-ai
cohere
- LangChain
- tiktoken
sentence-transformers
dashscope
- fastembed
- flagembedding
- llama-cloud
nltk
optimum-intel
- sentencepiece
- ai21
aleph-alpha-client
chonkie
- gigachat
- guidance
igptai
- konko
litellm
- mixedbread
- ModelScope
- octoai
- Ollama
- openvino
- openvino-genai
premai
- scikit-learn
- tritonclient
- vLLM
- voyageai
- zep-python
- zhipuai
- agent-search
- aimon
argilla-llama-index
assemblyai
- bm25s
browserbase
cleanlab-tlm
cognee
- colpali-engine
- datasets
- exa-py
flashrank
- hnswlib
honeyhive
- instructorembedding
isaacus
langfuse
llmlingua
- llmsherpa
- marvin
mlx
- mlx-lm
nomic
notdiamond
optimum
optimum-habana
- paddleocr
peft
presidio-analyzer
presidio-anonymizer
promptlayer
- psychicapi
- pydi-client
- rank-llm
- span-marker
- superlinked
tokenizers
uptrain
vectorize-client
videodb
- bleach
camelot-py
- ghostscript
- llama-index-readers-file
- llama-index-readers-youtube-transcript
- maincontentextractor
marker-pdf
markupsafe
mistune
- nbformat
- newspaper3k
nougat-ocr
- pandocfilters
webencodings
- xlrd
pillow
- bs4
- html2text
unstructured
pymupdf
- filetype
- bagel
- docx2txt
olefile
- pytesseract
dgml-utils
docling
- layoutir
- llama-parse
- lxml-html-clean
- nbconvert
pypdf
pypdf2
- striprtf
- svglib
- tika
tinytag
- youtube-transcript-api
- fastjsonschema
- fqdn
- jsonschema-specifications
marshmallow
- referencing
- rfc3339-validator
- rfc3986-validator
docling-core
- annotated-types
- jsonschema
opentelemetry-semantic-conventions
prometheus-client
- Alibaba Cloud
- oci
- OpenTelemetry
Side by side
mcpllama_index
SizeLines written by people and agents, without generated ones; code files, without tests.
mcp970,557 lines written1,184 code files
llama_index473,258 lines written2,055 code files
Who writes itA commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
mcp2.4% of its commits signed by AIWith Claude Code, GitHub Copilot, and Codex
llama_index0.2% of its commits signed by AIWith Claude Code, Cursor, and GitHub Copilot
ActivityFrom GitHub and its history, on the day SeeRepo read it.
mcpLast push November 13, 20262,089 commits9,918 stars
llama_indexLast push November 11, 20267,967 commits52,885 stars
TestsThe files that test the code, and the share of code files a test imports.
mcp1,401 test files77.6% of its code files have a test that imports them
llama_index1,607 test files46.5% of its code files have a test that imports them
Frequently asked questions
Which is bigger, mcp or llama_index?
mcp, with 970,557 lines written; llama_index has 473,258.
The proof: awslabs/mcp's code at commit 5d58a6a
Which has more GitHub stars, mcp or llama_index?
llama_index, with 52,885 stars; mcp has 9,918.
The proof: run-llama/llama_index on GitHub
Which has more tests, mcp or llama_index?
llama_index, with 1,607 test files; mcp has 1,401.
Which was updated more recently, mcp or llama_index?
mcp: its last push was on November 13, 2026, and llama_index's on November 11, 2026.
The proof: awslabs/mcp's commits on GitHub
Which has more commits signed by AI, mcp or llama_index?
mcp: an AI signed 2.4% of its commits, with Claude Code, GitHub Copilot, and Codex; in llama_index, 0.2%.
The proof: the commits each tool signed in awslabs/mcp
See inside your code, today.
Paste your repo and see it drawn, part by part: a medium one in under a minute.
Free, no account.

