CodeCanvas MCP
Evidence-backed code intelligence for Python coding agents.
CodeCanvas is a local static-analysis Model Context Protocol server. It answers questions about call paths, control flow, and change impact without forcing an agent to grep through an entire repository and infer the architecture from partial text matches.
On a blinded three-task Google ADK holdout, the logic_flow-only profile used
52.58% fewer server-reported input + output tokens than a built-in-tools
baseline, with mean rubric scores of 99.5/100 versus 100/100. Uncached input +
output fell 14.39%; the repository documents the full methodology and the
simple task that regressed.
Quick start
Python 3.10 or newer is required.
claude mcp add codecanvas -- uvx codecanvas-mcp
Claude Code and Codex users can install the plugin instead, which registers the server and its full tool catalog in one step:
claude plugin marketplace add donggyun112/codecanvas
claude plugin install codecanvas@codecanvas
For another MCP client, use the equivalent stdio configuration:
{
"mcpServers": {
"codecanvas": {
"command": "uvx",
"args": ["codecanvas-mcp"]
}
}
}
Pass an absolute project_path on the first tool call. CodeCanvas remembers the
last explicitly selected project for the rest of the server session.
Tools
| Tool | Answers |
|---|---|
project_status |
Which Python project is active, and is its analysis cached or ambiguous? |
list_entrypoints |
What FastAPI routes, scripts, function entrypoints, and public library exports exist? |
find_symbols |
Where is a function, method, or class by name or meaning? |
logic_flow |
What is this function's compact branch, outcome, downstream-call, and effect story? |
who_calls |
Who calls this function, directly or transitively? |
call_tree |
What project code does this function reach, and where are the effects? |
what_does |
What are this function's signature, calls, effects, exceptions, and direct risk? |
function_flow |
How does this function branch? |
reaching_conditions |
Which guards lead to each return or raise? |
verify_claim |
Does a qualified source reaches target claim hold under the observed paths and guards? |
analyze_impact |
Which entrypoints or public surfaces can an inline diff or git ref affect? |
validate_state_schema |
Do a function's state reads, writes, and returns agree with a supplied schema? |
simulate_state_transition |
What happens for focused state cases, invariants, and dependency overrides? |
Evidence-first responses
Static analysis is not runtime truth, so CodeCanvas exposes uncertainty instead
of hiding it. Successful responses identify the selected analysis_root and
report evidence strength, inferred or ambiguous edges, truncation, and whether
the result is safe to summarize as an unconditional claim.
verify_claim returns true, false, or uncertain. Unsupported qualifiers
and inferred-only paths cannot silently become a definite true.
Scope and safety
- CodeCanvas analyzes Python source with AST-based call-graph and control-flow analysis.
- FastAPI routes and
Depends()chains, scripts, and distributed package exports are recognized as entrypoints. - Compatible analysis is cached locally under
<project>/.codecanvas/. - Dynamic imports, reflection, monkey patching, and runtime-only values may remain unresolved and are reported as qualifications where possible.
simulate_state_transitionimports and executes trusted project code in a separate process. It is not a security sandbox; the imported code may access the filesystem, network, or subprocesses and may have import-time effects.
The complete guide, agent instruction snippet, benchmark command, and development setup are available in the GitHub repository.
License
CodeCanvas MCP is open-source software licensed under the MIT License.
Metadata
Release files for codecanvas-mcp 0.1.20
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| codecanvas_mcp-0.1.20.tar.gz | 270.1 kB | Without provenance | Details for codecanvas_mcp-0.1.20.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| codecanvas_mcp-0.1.20-py3-none-any.whl | Python 3 | none | any | Details for codecanvas_mcp-0.1.20-py3-none-any.whl |
Total release size: 470.2 kB
Release files / codecanvas_mcp-0.1.20.tar.gz
| Download URL | codecanvas_mcp-0.1.20.tar.gz |
|---|---|
| Size | 270.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1da534308c0f35d13d8508c71890c2729892c0e2a197b7bdb4c89fdbd93f0a2e
|
|
BLAKE2b-256 checksum How to use checksums |
c0bdf7dd4a72af6906757a6f0c7a6b16568ffe0295aca92e5bf25712cee1661e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.6 {"installer":{"name":"uv","version":"0.12.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Release files / codecanvas_mcp-0.1.20-py3-none-any.whl
| Download URL | codecanvas_mcp-0.1.20-py3-none-any.whl |
|---|---|
| Size | 200.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2ab10e06f8e98edce5929f141d0824347f0ab06113e2e62ee430e9c125232489
|
|
BLAKE2b-256 checksum How to use checksums |
6d3f9bfba876fd0598a36a263ab69c8f0516834751d98f1e849a90a9a821c2f9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.6 {"installer":{"name":"uv","version":"0.12.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
|
Security for codecanvas-mcp 0.1.20
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.