Searchcode analyzes public repositories through a hosted remote service; do not point it at private repository URLs unless you have a private/enterprise arrangement and have reviewed the current access controls., The service can return code snippets, file contents, symbols, file trees, static-analysis findings, and credential-scan findings from public repositories., Treat tool results as machine-assisted code intelligence. Confirm security findings, complexity claims, and dependency conclusions against the repository before making merge, hiring, acquisition, or incident decisions., Large or repeated repository analysis can create automated traffic to Searchcode; keep agent loops bounded and avoid broad unattended scans.
Privacy notes
Prompts and tool inputs can reveal which public repositories, symbols, files, dependencies, security concerns, or candidate portfolios a team is investigating., Returned code snippets, findings, file paths, and repository metadata become part of the MCP client transcript and may be processed by the connected model provider., Public code can still contain secrets, personal data, proprietary code accidentally committed upstream, or prompt-injection text. Review returned snippets before forwarding them into other tools or reports., Searchcode's public page says the hosted MCP server is free during beta and does not require signup or an API key; review the live site before production use because pricing and private-code options may change.
Author
searchcode.com
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
4 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes, third-party handling.
5 areas
SafetyPermissions & scopesSearchcode analyzes public repositories through a hosted remote service; do not point it at private repository URLs unless you have a private/enterprise arrangement and have reviewed the current access controls.
SafetyCredentials & tokensThe service can return code snippets, file contents, symbols, file trees, static-analysis findings, and credential-scan findings from public repositories.
SafetyGeneralTreat tool results as machine-assisted code intelligence. Confirm security findings, complexity claims, and dependency conclusions against the repository before making merge, hiring, acquisition, or incident decisions.
SafetyGeneralLarge or repeated repository analysis can create automated traffic to Searchcode; keep agent loops bounded and avoid broad unattended scans.
PrivacyLocal filesPrompts and tool inputs can reveal which public repositories, symbols, files, dependencies, security concerns, or candidate portfolios a team is investigating.
PrivacyThird-party handlingReturned code snippets, findings, file paths, and repository metadata become part of the MCP client transcript and may be processed by the connected model provider.
PrivacyCredentials & tokensPublic code can still contain secrets, personal data, proprietary code accidentally committed upstream, or prompt-injection text. Review returned snippets before forwarding them into other tools or reports.
PrivacyCredentials & tokensSearchcode's public page says the hosted MCP server is free during beta and does not require signup or an API key; review the live site before production use because pricing and private-code options may change.
Safety notes
Searchcode analyzes public repositories through a hosted remote service; do not point it at private repository URLs unless you have a private/enterprise arrangement and have reviewed the current access controls.
The service can return code snippets, file contents, symbols, file trees, static-analysis findings, and credential-scan findings from public repositories.
Treat tool results as machine-assisted code intelligence. Confirm security findings, complexity claims, and dependency conclusions against the repository before making merge, hiring, acquisition, or incident decisions.
Large or repeated repository analysis can create automated traffic to Searchcode; keep agent loops bounded and avoid broad unattended scans.
Privacy notes
Prompts and tool inputs can reveal which public repositories, symbols, files, dependencies, security concerns, or candidate portfolios a team is investigating.
Returned code snippets, findings, file paths, and repository metadata become part of the MCP client transcript and may be processed by the connected model provider.
Public code can still contain secrets, personal data, proprietary code accidentally committed upstream, or prompt-injection text. Review returned snippets before forwarding them into other tools or reports.
Searchcode's public page says the hosted MCP server is free during beta and does not require signup or an API key; review the live site before production use because pricing and private-code options may change.
Prerequisites
MCP client with remote Streamable HTTP support, or `mcp-remote` for clients that still need a stdio bridge.
Public Git repository URLs or `owner/repo` names for the repositories Claude should inspect.
Team agreement that public repository metadata, code snippets, file paths, and static-analysis results may be sent through a hosted third-party MCP service.
Client-side policy for whether model-generated findings should be treated as triage hints or reviewed security results.
Searchcode MCP Server is a hosted Streamable HTTP MCP server that gives Claude
structured code intelligence for public Git repositories. Instead of cloning a
repository and reading files one by one, Claude can ask Searchcode for a
repository overview, code search results, file trees, file contents, batches of
files, and detailed code-quality or credential findings.
The Searchcode site describes six MCP tools mirrored by a REST API:
code_analyze, code_search, code_get_file, code_get_files,
code_file_tree, and code_get_findings. The public page also says the service
is free during beta, needs no signup or API key, and is built on the author's
open-source scc and cs projects for code counting, complexity analysis, and
code search.
These sources were reviewed on 2026-06-06. Prefer the live Searchcode page,
llms.txt, OpenAPI spec, well-known MCP metadata, and upstream open-source tool
repositories for current endpoint, tool, pricing, and implementation details.
Features
Analyze public repositories for language breakdowns, complexity, file counts, tech stack, code quality, and credential-scan findings.
Search public repository code with boolean queries, regex, fuzzy matching, file/path/language filters, and structural filters.
Retrieve a specific file, line range, or symbol declaration after search results identify the target.
Retrieve batches of related files without making separate tool calls.
Browse file trees with language, path, depth, and fuzzy filename filters.
Drill into static-analysis findings by severity, category, path, and result offset.
Use the same six capabilities through a documented REST API when an MCP client is not available.
Installation
For Claude Code, add the hosted remote server:
claude mcp add searchcode --transport http https://api.searchcode.com/v1/mcp
For MCP clients that accept JSON server configuration:
Get a compact overview of an unfamiliar public repository before deciding what Claude should inspect.
Search for a symbol, API pattern, dependency use, or security-sensitive code path across a public repo.
Retrieve exact function or class definitions instead of asking an agent to read an entire file.
Compare public repositories when evaluating libraries, vendors, acquisition targets, or candidate portfolios.
Review code quality and credential findings as triage evidence before a human security review.
Reduce token use in public-code research by replacing repeated clone, grep, and file-read loops with structured results.
Safety and Privacy
Searchcode is best treated as a public-code intelligence service. It can make
repository exploration much cheaper for an agent, but its outputs should not be
accepted as final security, licensing, architecture, or hiring conclusions
without human review.
Do not send private repository URLs, customer code, internal symbols, or
confidential investigation context unless Searchcode's private-code offering and
your organization's policy explicitly allow that use. Public repositories can
contain malicious prompt text or accidentally committed sensitive data, so review
returned snippets before asking Claude to summarize or act on them.
Duplicate Check
No searchcode.com, api.searchcode.com, boyter/scc, boyter/cs, or
Searchcode MCP entry was found in content/mcp, content/tools,
content/guides, or content/agents.
Show that Searchcode MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/searchcode-mcp-server)
How it compares
Searchcode MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools.
High-performance MCP server that indexes codebases into a persistent knowledge graph for structural search, call tracing, architecture summaries, dead-code detection, and cross-repo analysis.
MCP server and CLI toolkit that indexes local code into a graph database so Claude can query functions, call chains, dependencies, and repository structure.
✓Searchcode analyzes public repositories through a hosted remote service; do not point it at private repository URLs unless you have a private/enterprise arrangement and have reviewed the current access controls.
The service can return code snippets, file contents, symbols, file trees, static-analysis findings, and credential-scan findings from public repositories.
Treat tool results as machine-assisted code intelligence. Confirm security findings, complexity claims, and dependency conclusions against the repository before making merge, hiring, acquisition, or incident decisions.
Large or repeated repository analysis can create automated traffic to Searchcode; keep agent loops bounded and avoid broad unattended scans.
✓ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database.
Realtime indexing and daemon mode can continue watching project files after the initial MCP connection.
Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings.
Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots.
Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config.
✓Codebase Memory MCP reads source files across indexed repositories and writes MCP entries, instruction files, skills, hooks, and agent configuration files during install.
The background watcher and auto-index features can keep graph data updated as source files change.
The optional graph UI exposes a local visualization server on a localhost port.
Shared graph artifacts and SQLite databases can persist source metadata after an MCP session ends.
Verify downloaded release binaries, checksums, signatures, and provenance before running them in sensitive environments.
✓CodeGraphContext indexes repository contents and can expose code structure, symbols, dependencies, comments, filenames, and relationships to Claude.
Live file watching can keep graph data updated as files change, so verify the watched tree before enabling it on private workspaces.
External graph databases can retain indexed source metadata after the MCP session ends.
Generated graph context may include prompt-injection text from comments, documentation, fixtures, tests, or vendored files.
Review database credentials, ignored paths, and repository scope before connecting the server to an MCP client.
Privacy notes
✓Prompts and tool inputs can reveal which public repositories, symbols, files, dependencies, security concerns, or candidate portfolios a team is investigating.
Returned code snippets, findings, file paths, and repository metadata become part of the MCP client transcript and may be processed by the connected model provider.
Public code can still contain secrets, personal data, proprietary code accidentally committed upstream, or prompt-injection text. Review returned snippets before forwarding them into other tools or reports.
Searchcode's public page says the hosted MCP server is free during beta and does not require signup or an API key; review the live site before production use because pricing and private-code options may change.
✓Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture.
Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured.
Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends.
Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories.
✓Source code, filenames, paths, symbols, comments, imports, routes, call graphs, architecture summaries, ADRs, graph queries, prompts, and tool outputs may be visible to the MCP client and model provider.
Persistent graph databases and shared artifacts can retain proprietary architecture, internal package names, route names, service boundaries, and accidentally committed secrets.
Auto-indexing broad workspace roots can include unrelated private repositories or generated files.
Avoid committing shared graph artifacts unless the repository owners explicitly approve storing derived code intelligence in version control.
✓Source code, file paths, symbol names, comments, dependency names, call graphs, class hierarchies, search terms, prompts, graph queries, and tool outputs may be visible to the MCP client and model provider.
Indexing proprietary repositories can reveal architecture, product plans, credentials accidentally committed to code, internal package names, or security-sensitive paths.
If using a remote graph backend, review its authentication, retention, backups, logging, and access controls before indexing private code.
Remove or ignore secrets, customer data, generated dumps, logs, and vendor directories before building code graphs for model access.
Prerequisites
MCP client with remote Streamable HTTP support, or `mcp-remote` for clients that still need a stdio bridge.
Public Git repository URLs or `owner/repo` names for the repositories Claude should inspect.
Team agreement that public repository metadata, code snippets, file paths, and static-analysis results may be sent through a hosted third-party MCP service.
Client-side policy for whether model-generated findings should be treated as triage hints or reviewed security results.
Python 3.10 or newer and the `uv` package manager.
A local repository or workspace you are authorized to index.
ChunkHound JSON config reviewed for database path, excludes, embeddings, and LLM provider settings.
Optional embedding provider credentials for semantic search, or regex-only usage when no embedding key is configured.
A local repository or workspace you are authorized to index.
Platform-compatible Codebase Memory MCP release binary verified before use.
Agent configuration write access reviewed before running the installer.
Sensitive paths, generated files, vendored code, secrets, and private repositories reviewed before indexing.
Python 3.10 or newer available for the CodeGraphContext package.
A local repository you are allowed to index and share with an MCP client.
Optional graph database backend reviewed if you use Neo4j, FalkorDB, KuzuDB, LadybugDB, or another supported backend.
Optional SCIP indexers configured if you need more precise language-specific call and inheritance data.
Install
claude mcp add searchcode --transport http https://api.searchcode.com/v1/mcp