Skip to main content
Glama
dalebrubaker

sourcegraph-mcp

by dalebrubaker
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

sourcegraph-mcp

Model Context Protocol server for searching code via SourceGraph's GraphQL API. Leverages SourceGraph's indexed symbol search for fast, precise code navigation. Works with both local and cloud SourceGraph instances.

Why Use This?

Search your entire codebase instantly using SourceGraph's indexed search:

  • Lightning Fast: Symbol lookups in <100ms using indexed search

  • Precise: Find exact definitions vs references/usages separately

  • Cost-effective: ~400 tokens per search vs 50k+ tokens loading files

  • Comprehensive: Search across all repos, branches, and languages

Related MCP server: @codesift/mcp

Key Features

🎯 Symbol Search (Indexed)

  • Find Definitions: Locate where functions, classes, methods are declared

  • Find References: See all places where a symbol is used

  • Fast Lookups: Uses SourceGraph's pre-built symbol index

  • Returns: Exact file path, line number, and column position

🔍 Code Search

  • Text Search: Find any text pattern across your codebase

  • Regex Search: Complex pattern matching with full regex support

  • Filters: By repository, file path, language, and more

Installation

Quick Start (with pipx - Recommended)

pipx install sourcegraph-mcp

This installs the sourcegraph-mcp command globally and handles all dependencies automatically.

Verify Installation

which sourcegraph-mcp
# Should show: /Users/yourusername/.local/bin/sourcegraph-mcp

Configuration

IMPORTANT: Replace the URL and token with your actual SourceGraph instance details.

Option 1: Environment Variables (Recommended)

export SOURCEGRAPH_URL=http://localhost:3370
export SOURCEGRAPH_TOKEN=sgp_your_token_here

Option 2: Config File

Create config.json:

{
  "sourcegraph_url": "http://localhost:3370",
  "access_token": "sgp_your_token_here",
  "timeout": 30
}

Option 3: CLI Arguments

sourcegraph-mcp --url http://localhost:3370 --token sgp_your_token_here

Setup with MCP Clients

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

IMPORTANT: Replace the URL and token with your actual SourceGraph instance details.

{
  "mcpServers": {
    "sourcegraph": {
      "command": "sourcegraph-mcp",
      "env": {
        "SOURCEGRAPH_URL": "http://localhost:3370",
        "SOURCEGRAPH_TOKEN": "sgp_your_token_here"
      }
    }
  }
}

Claude Code

Important: First install with pipx install sourcegraph-mcp, then configure.

IMPORTANT: Replace the URL and token with your actual SourceGraph instance details.

Option 1: User-Wide (Recommended - No Permission Prompts)

Add to ~/.claude.json:

{
  "mcpServers": {
    "sourcegraph": {
      "command": "sourcegraph-mcp",
      "env": {
        "SOURCEGRAPH_URL": "http://localhost:3370",
        "SOURCEGRAPH_TOKEN": "sgp_your_token_here"
      }
    }
  },
  "permissions": {
    "allow": [
      "mcp__sourcegraph__*"
    ]
  }
}

Note: If sourcegraph-mcp is not in your PATH, use the full path:

"command": "/Users/yourusername/.local/bin/sourcegraph-mcp"

Restart Claude Code and verify with /mcp command.

Option 2: Project-Specific

Create .mcp.json in your project root:

{
  "mcpServers": {
    "sourcegraph": {
      "command": "sourcegraph-mcp",
      "env": {
        "SOURCEGRAPH_URL": "http://localhost:3370",
        "SOURCEGRAPH_TOKEN": "sgp_your_token_here"
      }
    }
  }
}

Then add permissions to .claude/settings.local.json:

{
  "permissions": {
    "allow": [
      "mcp__sourcegraph__find_symbol_definition",
      "mcp__sourcegraph__find_symbol_references",
      "mcp__sourcegraph__search_sourcegraph",
      "mcp__sourcegraph__search_sourcegraph_regex",
      "mcp__sourcegraph__get_sourcegraph_config"
    ]
  },
  "enableAllProjectMcpServers": true,
  "enabledMcpjsonServers": ["sourcegraph"]
}

Important: Permission format must use mcp__servername__toolname with double underscores, not colons.

Note: The permissions section above is specific to Claude Code. Other MCP clients may not require explicit permissions or may use different permission systems.

Other MCP Clients (Cursor, Windsurf, Zed, Cline, etc.)

Most MCP clients use similar configuration. The general pattern is:

  1. Install: pipx install sourcegraph-mcp

  2. Add to your client's MCP config file:

{
  "mcpServers": {
    "sourcegraph": {
      "command": "sourcegraph-mcp",  // or full path: ~/.local/bin/sourcegraph-mcp
      "env": {
        "SOURCEGRAPH_URL": "http://localhost:3370",
        "SOURCEGRAPH_TOKEN": "sgp_your_token_here"
      }
    }
  }
}

Refer to your client's documentation for the config file location.

Community contributions welcome! If you've successfully set this up with another client, please submit a PR with instructions.

Usage

Once configured, your AI assistant can leverage SourceGraph's indexed search:

Symbol Definitions (Fast Lookups)

"Find where the ProcessOrder function is defined"
"Where is the CustomerService class declared?"
"Show me the definition of HandleRequest method"
"Locate the API_KEY constant definition"

Symbol References (Find Usages)

"Find all calls to ProcessOrder"
"Where is CustomerService used?"
"Show me all references to API_KEY"
"Find everywhere HandleRequest is called"

General Code Search

"Search for authentication code"
"Find TODO comments in C# files"
"Show error handling patterns in the api directory"

Available Tools

1. find_symbol_definition

Find where symbols are defined (declarations). Returns exact file path and line number.

Best for:

  • "Where is X defined?"

  • "Go to definition of Y"

  • "Show me the declaration of Z"

Returns:

  • File path

  • Line number

  • Column position

  • Symbol kind (function, class, method, etc.)

2. find_symbol_references

Find where symbols are used (references/calls). Returns all usage locations.

Best for:

  • "Where is X called?"

  • "Find all uses of Y"

  • "Show me references to Z"

Returns:

  • File paths and line numbers for each usage

  • Code context around each reference

3. search_sourcegraph

General text-based code search with full query syntax.

Query syntax:

  • repo:owner/name - Filter by repository

  • file:pattern - Filter by file path

  • lang:language - Filter by programming language

  • case:yes - Case-sensitive search

4. search_sourcegraph_regex

Search using regular expressions for complex pattern matching.

5. get_sourcegraph_config

View current configuration (useful for debugging).

Performance Advantages

Symbol Search (Indexed)

  • ✅ <100ms: Instant lookups using pre-built index

  • ✅ Precise: Distinguishes definitions from references

  • ✅ Scalable: Works across millions of lines of code

Text Search

  • ✅ Fast: Leverages SourceGraph's Zoekt indexing

  • ✅ Flexible: Full regex and filter support

  • ✅ Comprehensive: Searches across all content

vs Loading Files into Context

  • 400 tokens per search vs 50k+ tokens loading files

  • Instant results vs waiting for file loads

  • Pinpoint accuracy vs reading through entire files

Getting a SourceGraph Token

  1. Navigate to your SourceGraph instance

  2. Go to Settings → Access tokens

  3. Click "Generate new token"

  4. Copy the token (starts with sgp_)

Local Development

# Clone and install
git clone https://github.com/dalebrubaker/sourcegraph-mcp
cd sourcegraph-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .

# Test configuration
python test_connection.py

# Run with config file
python server.py

# Run with CLI args
python server.py --url http://localhost:3370 --token sgp_your_token_here

Troubleshooting

"Could not connect to MCP server"

  • Verify SourceGraph is running and accessible

  • Check URL format (include http:// or https://)

  • Test token: curl -H "Authorization: token sgp_..." http://your-url/.api/graphql

  • Verify installation: which sourcegraph-mcp should show the installed path

  • If not in PATH, use full path in config: /Users/yourusername/.local/bin/sourcegraph-mcp

"Command not found"

  • Make sure you installed with pipx install sourcegraph-mcp

  • Check if ~/.local/bin is in your PATH: echo $PATH | grep .local/bin

  • Try using the full path in your config instead of just sourcegraph-mcp

"No symbols found"

  • Symbol search requires SourceGraph's symbol indexing to be enabled

  • Check if your repositories have been indexed: Settings → Repositories → Indexing

  • Symbol indexing may take time for large repos

  • Try general code search as a fallback

Testing Your Setup

# Test connection and both search types
python test_connection.py

Example Queries

Finding Definitions

User: "Find where the LowerBound method is defined with file name and line number"

MCP Response:
## 1. `LowerBound` (method)
**File:** `src/Collections/SortedList.cs`
**Line:** 142
**Position:** Line 142, Column 8
**Repository:** `myorg/core-lib`

Finding References

User: "Show me all places where ProcessOrder is called"

MCP Response:
## 1. `OrderController.cs`
**Repository:** `myorg/api-service`
**URL:** https://sourcegraph.local/...

**Matches:**
- **Line 45:** `var result = await ProcessOrder(orderId);`
- **Line 87:** `return ProcessOrder(order);`

## 2. `OrderProcessor.cs`
...

License

MIT

Contributing

PRs welcome! Please open an issue first to discuss significant changes.

Roadmap

  • Support for batch symbol lookups

  • Cached symbol results for faster repeated queries

  • Structural search support

  • Commit and diff search tools

  • Multi-repo symbol search optimization

Available Tools

5 tools
find_symbol_definitionA

Find where a symbol (function, class, method, variable, constant) is DEFINED in the codebase. Returns the exact file path and line number where the symbol is declared.

This uses SourceGraph's indexed symbol search for fast lookups. Perfect for 'go to definition' or 'where is X defined?' queries.

Returns: File path, line number, and column position of the definition.

Examples:

  • Find where the ProcessOrder function is defined

  • Locate the definition of class CustomerService

  • Find where variable API_KEY is declared

  • Show me where the HandleRequest method is defined

Tips:

  • Use symbol_kind filter to narrow results (function, class, method, variable)

  • Use repo_filter to search specific repositories (e.g., 'repo:myorg/myrepo')

  • Searches are case-sensitive by default

Note: To find where a symbol is USED (not defined), use find_symbol_references instead.

ParametersJSON Schema
NameRequiredDescriptionDefault
symbol_nameYesName of the symbol to find (e.g., 'ProcessOrder', 'CustomerService', 'API_KEY')
symbol_kindNoOptional: Filter by symbol kind to narrow results
repo_filterNoOptional: Filter by repository (e.g., 'repo:owner/name' or 'repo:^github\.com/org/project$')
max_resultsNoMaximum number of results (default: 10)

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but the description discloses the use of SourceGraph's indexed search, return format (file path, line, column), and tips. Could be more explicit about being a read-only operation, but overall adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with clear sections: description, returns, examples, tips, note. Concise and front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no output schema, and the complexity of symbol definition lookup, the description covers purpose, parameters, usage, return values, and sibling differentiation comprehensively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All parameters have schema descriptions, and the tool description adds value with examples, tips (case-sensitivity, filters), and usage context that extends beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds where a symbol (function, class, etc.) is DEFINED, using specific verbs and resource. It distinguishes from sibling find_symbol_references.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('go to definition' queries) and when not to use (for symbol usage, use find_symbol_references). Provides clear alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

find_symbol_referencesA

Find all places where a symbol is USED/REFERENCED in the codebase. Returns file paths and line numbers for each usage.

This searches for actual code references, not the definition. Use this to see where a function is called, a class is instantiated, a method is invoked, or a variable is accessed.

Returns: File paths and line numbers showing code context for each reference.

Examples:

  • Find all calls to the ProcessOrder function

  • See where CustomerService class is instantiated

  • Find all references to API_KEY variable

  • Show me everywhere HandleRequest is called

Tips:

  • Use repo_filter to search specific repositories

  • Use file_filter to narrow down to specific files or directories

  • Add lang:csharp (or other language) to filter by programming language

Note: To find where a symbol is DEFINED, use find_symbol_definition instead.

ParametersJSON Schema
NameRequiredDescriptionDefault
symbol_nameYesName of the symbol to find references for
repo_filterNoOptional: Filter by repository (e.g., 'repo:owner/name')
file_filterNoOptional: Filter by file path (e.g., 'file:\.cs$' for C# files)
lang_filterNoOptional: Filter by language (e.g., 'csharp', 'python', 'javascript')
max_resultsNoMaximum number of results (default: 20)

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses behavior: returns file paths and line numbers, searches across repos, supports filters. Minor omission: doesn't mention max_results default or any limitations like result size.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise, well-structured with clear headings (Returns, Examples, Tips, Note). Front-loaded with main purpose, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-param tool with no output schema, the description is fairly complete: explains what is returned, gives examples, and details filters. Minor gap: doesn't mention max_results default or pagination behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage, each parameter has description. The description adds examples and context but doesn't significantly enhance meaning beyond schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it finds where a symbol is USED/REFERENCED, returning file paths and line numbers. It distinguishes from sibling tool find_symbol_definition by explicitly saying use that for definitions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells when to use this tool (for references) and when not (for definitions, use find_symbol_definition). It also provides tips on using filters, which guides effective usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_sourcegraph_configA

Get current SourceGraph MCP server configuration. Shows the configured URL and whether an access token is set. Useful for debugging connection issues.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the burden. It discloses the specific data returned (configured URL and whether an access token is set). No side effects are mentioned, but for a read-only config getter, this is acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The first sentence states the purpose, the second adds detail and use case. Highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple parameterless tool with no output schema, the description fully explains what the tool does and what it returns. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and schema coverage is 100%. The description adds value by explaining what the output contains, going beyond the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves the SourceGraph MCP server configuration, listing specific items (URL, token status). It is distinct from sibling tools which focus on searching and symbol operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly mentions usefulness for debugging connection issues, providing clear context for when the tool should be used. However, it does not explicitly exclude alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_sourcegraphA

General code search across your SourceGraph instance. Use this for text-based searches, finding patterns, or when you need to search for more than just symbol definitions.

Supports full SourceGraph query syntax including:

  • repo:owner/name - Filter by repository

  • file:pattern - Filter by file path

  • lang:language - Filter by programming language

  • case:yes - Case-sensitive search

  • Regular expressions and literals

Examples:

  • 'PlaceOrder lang:csharp' - Find PlaceOrder in C# files

  • 'repo:myorg/myrepo TODO' - Find TODOs in a specific repo

  • 'file:.py$ import pandas' - Find pandas imports in Python files

  • 'error handling lang:java' - Search for error handling in Java

Note: For finding symbol definitions or references specifically, use find_symbol_definition or find_symbol_references for faster, more accurate results.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query using SourceGraph syntax
max_resultsNoMaximum number of results (default: 10)

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses supported source syntax and query features with examples, but lacks details on output format or error behavior. Since no annotations exist, description carries burden and does well overall.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with bullet points and examples, no wasted words, front-loaded with clear purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and only two parameters, the description is thorough. Missing explicit mention of output format, but examples imply it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers both parameters (100% coverage), and description adds examples and syntax details beyond the schema's param descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it's for 'general code search' across SourceGraph, and distinguishes from sibling tools for symbol definitions and references.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises when to use this tool versus find_symbol_definition or find_symbol_references, and provides query syntax examples.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_sourcegraph_regexA

Search code using regular expressions. Automatically sets patternType to 'regexp' for regex queries. Use this for complex pattern matching.

Examples:

  • 'class \w+Service' - Find all service classes

  • 'def (get|set)_\w+' - Find getter/setter methods

  • 'TODO|FIXME|HACK' - Find code comments

  • 'function \w+(.*) {' - Find function declarations

Tips:

  • Use filters parameter for additional constraints

  • Combine with repo:, file:, and lang: filters

  • Remember to escape backslashes in regex patterns

ParametersJSON Schema
NameRequiredDescriptionDefault
patternYesRegular expression pattern to search for
filtersNoAdditional filters (e.g., 'repo:owner/name lang:python')
max_resultsNoMaximum number of results (default: 10)

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that it automatically sets patternType to 'regexp' and reminds users to escape backslashes. However, with no annotations provided, it does not cover potential performance issues, limitations, or authentication requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with clear sections (examples, tips). It uses bullet points for readability. Could be slightly shorter without losing key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lacks explanation of the return format (no output schema) and does not mention authentication or API context. However, it provides useful examples and tips.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents parameters. The description adds examples and tips for the pattern parameter and mentions filters, but this is not substantial beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool searches code using regular expressions for complex pattern matching. It distinguishes itself from siblings like search_sourcegraph (likely literal) and find_symbol_*, making its purpose specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description advises 'Use this for complex pattern matching' and provides examples and tips on combining with filters. It implicitly suggests alternatives but does not explicitly state when not to use it or exclude literal searches.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

Each tool targets a distinct operation: symbol definition, symbol references, general text search, regex search, and server configuration. Even the two search tools are clearly differentiated by pattern type, minimizing ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with underscores (e.g., find_symbol_definition, search_sourcegraph). The naming is descriptive and predictable across the set.

Tool Count5/5

With 5 tools, the set is compact yet covers the core functionalities of code search: definition lookup, reference lookup, general search, regex search, and configuration. No redundancy or bloat.

Completeness5/5

The tool surface comprehensively covers the primary use cases for a code search server: locating symbol definitions, finding usages, performing text/regex searches, and retrieving config. No obvious missing operations for the intended domain.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Zoekt MCP Server

    najva-ai
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that provides code search capabilities for AI tools and LLMs using Zoekt, allowing for searching across codebases with advanced query syntax and content fetching.
    22
    MIT

  • sourcegraph-mcp

    akbad
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server exposing Sourcegraph's AI-enhanced code search capabilities to coding agents, enabling advanced code search, repository discovery, and content fetching.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dalebrubaker/sourcegraph-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server