Skip to main content
Glama
pkt-lab

mcp-bitbake

by pkt-lab
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

mcp-bitbake

A deterministic MCP (Model Context Protocol) server for BitBake/Yocto. Inspects recipe metadata without evaluating variables — returns only raw assignments as found in files.

Design rules:

  • Never evaluates variables — only returns raw assignments

  • Only supports .bb and .bbappend files

  • Supported operators: =, :=, ?=, +=, .=

  • Returns structured JSON for all responses

  • Fails closed on unsupported syntax (override syntax warned, not parsed)

Install

From GitHub (no npm publish needed):

npm install github:pkt-lab/mcp-bitbake

Or clone and build manually:

git clone https://github.com/pkt-lab/mcp-bitbake
cd mcp-bitbake
npm install && npm run build

Related MCP server: Repo Docs MCP

Claude Desktop configuration

If installed via npm (GitHub):

{
  "mcpServers": {
    "mcp-bitbake": {
      "command": "node",
      "args": ["./node_modules/mcp-bitbake/dist/index.js"]
    }
  }
}

If cloned locally:

{
  "mcpServers": {
    "mcp-bitbake": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-bitbake/dist/index.js"]
    }
  }
}

Config file location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • Linux: ~/.config/Claude/claude_desktop_config.json

Restart Claude Desktop after editing.

MCP tools

find_recipe_files

Search recursively for .bb/.bbappend files matching a filename pattern:

{ "root_path": "/path/to/poky", "query": "busybox" }

Returns: { ok: true, matches: [{ path, file_type, filename }] }

scan_layer_recipe_files

List all .bb/.bbappend files under a layer path:

{ "layer_path": "/path/to/meta-mylayer" }

Returns: { ok: true, files: [{ path, file_type }] }

parse_recipe_file

Parse a single .bb or .bbappend file and return all raw variable assignments:

{ "file_path": "/path/to/meta-layer/recipes-core/myapp/myapp_1.0.bb" }

Returns: { ok: true, variables: [{ name, operator, raw_value, line }], warnings?: [...] }

  • Comments and python/shell function blocks are skipped

  • Override syntax (VAR:append, VAR:${PN}, etc.) is warned but not parsed

  • Multi-line values (lines ending with \) are concatenated into raw_value

get_recipe_var_raw

Get all assignments for a specific variable in a file:

{ "file_path": "/path/to/recipe.bb", "variable": "SRC_URI" }

Returns: { ok: true, assignments: [{ operator, raw_value, line }] }

Error format

All errors return:

{ "ok": false, "error_code": "...", "message": "..." }

Error codes: FILE_NOT_FOUND, INVALID_PATH, UNSUPPORTED_SYNTAX, INVALID_ARGUMENT

License

MIT

Available Tools

4 tools
find_recipe_filesA

Search recursively for .bb/.bbappend files matching a filename query under root_path.

ParametersJSON Schema
NameRequiredDescriptionDefault
root_pathYesDirectory to search recursively
queryYesSubstring to match against filenames

TDQS

A3.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions recursive searching and filename matching, but lacks details on permissions needed, error handling, output format, or performance considerations (e.g., depth limits, large directory handling). For a search tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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?

The description is a single, well-structured sentence that efficiently conveys the core functionality without redundancy. It is front-loaded with the main action and includes all essential elements (search type, file types, matching criteria, scope), making it easy to parse and understand quickly.

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?

Given the tool's moderate complexity (recursive file search), lack of annotations, and no output schema, the description is adequate but incomplete. It covers the basic operation but omits details on return values, error cases, and behavioral nuances that would help an agent use it correctly in varied contexts. It meets minimum viability but has clear gaps.

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 description coverage is 100%, so the schema already documents both parameters ('root_path' and 'query') adequately. The description adds minimal value by reinforcing that 'root_path' is the directory to search under and 'query' matches against filenames, but does not provide additional syntax, examples, or constraints beyond what the schema specifies. This meets the baseline for high schema coverage.

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 specific action ('Search recursively'), target resources ('.bb/.bbappend files'), and scope ('under root_path'), distinguishing it from sibling tools like 'parse_recipe_file' (which parses rather than searches) and 'scan_layer_recipe_files' (which may have different scoping). It uses precise technical terminology that aligns with the tool's domain.

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

Usage Guidelines3/5

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

The description implies usage for finding recipe files by filename substring matching, but it does not explicitly state when to use this tool versus alternatives like 'scan_layer_recipe_files' or 'get_recipe_var_raw'. No guidance is provided on prerequisites, exclusions, or comparative contexts, leaving the agent to infer usage from the description alone.

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

get_recipe_var_rawB

Get all raw assignments for a specific variable in a .bb or .bbappend file.

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the .bb or .bbappend file
variableYesVariable name to look up (e.g. SRC_URI, PN, PV)

TDQS

B3.1/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't describe how it behaves: it doesn't mention if it's read-only, what format the 'raw assignments' are returned in, whether it handles errors for missing files/variables, or any performance considerations. This leaves significant gaps for a tool with no annotation coverage.

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?

The description is a single, well-structured sentence that efficiently conveys the core purpose without any wasted words. It's front-loaded with the key action and resource, making it easy to parse quickly.

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?

Given the tool's moderate complexity (2 required parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks details on behavior, output format, and sibling differentiation. Without annotations or output schema, more context would be helpful, but it meets the minimum viable threshold.

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?

The input schema has 100% description coverage, with clear documentation for both parameters (file_path and variable). The description adds no additional parameter semantics beyond what's in the schema, such as examples of variable names beyond those listed or file path constraints. With high schema coverage, the baseline score of 3 is appropriate.

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

Purpose4/5

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

The description clearly states the action ('Get all raw assignments') and the target resource ('for a specific variable in a .bb or .bbappend file'), making the purpose immediately understandable. However, it doesn't explicitly differentiate this tool from its siblings (find_recipe_files, parse_recipe_file, scan_layer_recipe_files), which would be needed for a perfect score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus its siblings or alternatives. It mentions the specific file types (.bb or .bbappend) but doesn't explain why one would choose this tool over parse_recipe_file for variable assignments, leaving the agent to infer usage from context alone.

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

parse_recipe_fileA

Parse a single .bb or .bbappend file and return all raw variable assignments. Never evaluates variables.

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesAbsolute or relative path to the .bb or .bbappend file

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it parses a single file, returns raw assignments, and does not evaluate variables. However, it lacks details on error handling, performance, or output format, which are important for a parsing tool.

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?

The description is a single, efficient sentence that is front-loaded with the core purpose and includes a critical behavioral note ('never evaluates variables'). There is no wasted text, making it highly concise and well-structured.

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?

Given the tool's complexity (parsing with specific constraints), no annotations, and no output schema, the description is adequate but incomplete. It covers the basic operation and a key limitation, but lacks details on return values, error cases, or integration with sibling tools, leaving gaps for an agent.

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 description coverage is 100%, so the schema already documents the 'file_path' parameter fully. The description does not add any additional meaning or context beyond what the schema provides, such as file format constraints or examples, meeting the baseline for high coverage.

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 specific action ('parse'), the resource ('.bb or .bbappend file'), and the output ('all raw variable assignments'), distinguishing it from siblings like 'find_recipe_files' (which finds files) and 'get_recipe_var_raw' (which gets a specific variable). It explicitly notes it 'never evaluates variables,' which further clarifies its scope.

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

Usage Guidelines3/5

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

The description implies usage by specifying the file types (.bb or .bbappend) and the output (raw variable assignments), but it does not explicitly state when to use this tool versus alternatives like 'get_recipe_var_raw' or 'scan_layer_recipe_files.' No exclusions or prerequisites are mentioned.

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

scan_layer_recipe_filesB

List all .bb/.bbappend files under a Yocto layer path.

ParametersJSON Schema
NameRequiredDescriptionDefault
layer_pathYesRoot directory of the Yocto layer

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions listing files but doesn't disclose behavioral traits like whether it recursively searches subdirectories, handles errors, returns absolute/relative paths, or has any rate limits. The description is minimal and lacks operational context.

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?

The description is a single, efficient sentence with zero wasted words. It is appropriately sized for a simple tool and front-loads the core purpose without unnecessary elaboration.

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?

Given the tool's low complexity (one parameter, no output schema, no annotations), the description is minimally adequate but incomplete. It lacks details on output format, error handling, and behavioral traits, which are important for a file-listing operation without structured output documentation.

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 description coverage is 100% with one parameter ('layer_path') fully documented in the schema. The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline of 3 for high schema coverage.

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 specific action ('List all'), target resource ('.bb/.bbappend files'), and scope ('under a Yocto layer path'). It distinguishes from sibling tools like 'find_recipe_files' by specifying the exact file types and location context.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like 'find_recipe_files' or 'parse_recipe_file'. The description only states what it does without indicating appropriate contexts, prerequisites, or exclusions.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 4 tool updatesv1.0.0
    • First observedfind_recipe_files
    • First observedget_recipe_var_raw
    • First observedparse_recipe_file
    • First observedscan_layer_recipe_files
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0
Disambiguation4/5

The tools have mostly distinct purposes: find_recipe_files searches by filename, get_recipe_var_raw extracts a specific variable, parse_recipe_file parses all variables in a file, and scan_layer_recipe_files lists files in a layer. However, find_recipe_files and scan_layer_recipe_files both involve listing recipe files, which could cause some confusion about when to use each.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case, such as find_recipe_files, get_recipe_var_raw, parse_recipe_file, and scan_layer_recipe_files. This uniformity makes the set predictable and easy to understand.

Tool Count4/5

With 4 tools, the count is reasonable for a BitBake/Yocto-focused server, allowing for basic operations like searching, parsing, and listing. It might be slightly thin for advanced workflows, but it covers core needs without being overwhelming.

Completeness3/5

The tools provide good coverage for reading and parsing recipe files, but there are notable gaps for actions like evaluating variables, modifying recipes, or handling dependencies. This limits the server to inspection tasks, missing key operations for a full BitBake toolset.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

  • Code Scanner Server

    Ixe1
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that scans codebases to extract structural information (classes, functions, etc.) with flexible filtering options and outputs in LLM-friendly formats.
    1
    2
    GPL 3.0

  • Repo Docs MCP

    pepperfm
    A
    license
    Not graded
    quality
    D
    maintenance
    A generic MCP server that exposes local repository checkouts, allowing users to search and read code and documentation through natural language. It supports multiple instances, enabling seamless interaction with various codebases via configurable tool prefixes and URI schemes.
    2,013
    MIT

  • Repo Interrogator

    taggedzi
    A
    license
    A
    quality
    A
    maintenance
    A local-first MCP server that enables AI tools to safely inspect and search code repositories, providing indexing, deterministic BM25 search, code outlining, and context bundles without code modification.
    9
    1
    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/pkt-lab/mcp-bitbake'

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