Skip to main content
Glama
deenesjakoruzh
Patrizzos

envspeak

by Patrizzos
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

EnvSpeak

MCP server and CLI that resolves config/env-var cascade across .env files, Docker Compose, and Kubernetes — tells AI agents (and you) what a variable actually evaluates to at runtime, and why.

Same problem shape as CSS cascade — several sources, non-obvious precedence rules, and a value that "wins" only because of where it's defined — applied to application configuration instead of stylesheets. A sibling project to stylesafe and stylespeak, which do the same thing for CSS.

The problem

A real app's config comes from .env, .env.local, .env.production, docker-compose.yml (environment: vs env_file:), Kubernetes ConfigMap/Secret objects, and hard-coded fallbacks in code — five-plus layers, each with its own precedence rules that don't compose the way you'd guess. The best-known gotcha: a plain .env.local overrides .env.production unless you also have a .env.production.local — because "local" outranks "environment-specific" in the conventional dotenv cascade. An agent editing config has no way to know what a variable actually resolves to, or what breaks if it changes one layer.

Related MCP server: onboard-mcp

Tools

  • resolve_variable — what does DATABASE_URL actually evaluate to, and which file wins?

  • trace_variable — every place this variable is set, across every domain and environment.

  • impact_preview — if I change this value in this file, what actually changes downstream — and what's shielded by something higher-precedence?

  • config_manifest — a compressed, whole-project summary: every variable, its sources, and risk hotspots (secrets sitting in a tracked file, variables read in code with no fallback and no source anywhere).

  • diff_environments — resolve every variable under two environments/services/workloads and see what's actually different between them.

Install

npm install -g @patrizzos/envspeak

As an MCP server

{
  "mcpServers": {
    "envspeak": {
      "command": "envspeak"
    }
  }
}

As a CLI

envspeak resolve DATABASE_URL --environment production
envspeak trace LOG_LEVEL
envspeak impact --file .env --variable LOG_LEVEL --newValue debug
envspeak manifest
envspeak diff --a '{"nodeEnv":"development"}' --b '{"nodeEnv":"production"}'

If --files is omitted, envspeak auto-discovers .env*, Compose, and Kubernetes manifest files under --projectRoot (default: current directory). Pass --files a,b,c to scope it explicitly — recommended for MCP calls, so the agent controls exactly what's read.

Precedence conventions encoded

dotenv (Next.js/Vite-style, the de facto standard): process.env (shell) > .env.[env].local > .env.local > .env.[env] > .env > code fallback (process.env.X || 'default'). Note .env.local outranks .env.[env] — the gotcha above.

Docker Compose: docker compose run -e (CLI) > environment: > env_file: (last file in the list wins on conflicts) > Dockerfile ENV (not analyzed).

Kubernetes: inline env: always overrides envFrom: (bulk ConfigMap/Secret import; last entry in the list wins among those). Env values are frozen at pod start — editing a referenced ConfigMap/Secret does not reach a running pod without a restart or rollout. impact_preview flags this.

Every result includes a confidence level and a caveat string, because a shell-exported or CLI-passed override is always possible and never visible to static analysis — envspeak says so explicitly rather than pretending certainty it doesn't have.

Security

  • Zero runtime dependencies. The YAML subset parser used for Compose/Kubernetes files is hand-written rather than pulled in from npm, so there's no third-party supply-chain surface. npm audit is clean by construction.

  • Path-traversal guarded. File reads are resolved against projectRoot and refuse to escape it, even if a tool call is given a crafted relative path.

  • Prototype-pollution guarded. Object keys parsed from YAML content (__proto__, constructor, prototype) are never used for property assignment.

  • Secrets are redacted by default. Kubernetes Secret values are shown only as ab***yz, never in full, regardless of which tool surfaces them.

  • Secret-likelihood heuristics. Variable names and value shapes (AWS keys, GitHub tokens, PEM blocks, high-entropy credential-shaped strings) are flagged, cross-referenced against .gitignore, and surfaced as a secretFlag / risk hotspot rather than silently passed through.

  • Bounded, non-backtracking regexes. Pattern matching used for code-default scanning caps match length and avoids nested quantifiers to avoid ReDoS on large files.

  • Regardless of these guards, envspeak reads whatever files you point it at — scope the files list an agent can pass, the same way you'd scope any tool with filesystem access.

Development

npm test   # zero dependencies — no install step needed

License

MIT

Available Tools

5 tools
config_manifestB

Compressed, project-wide summary of every config variable found — sources, domains, and risk hotspots (likely secrets in tracked files, variables read in code with no source). Load once per session instead of repeated resolve_variable calls.

ParametersJSON Schema
NameRequiredDescriptionDefault
filesYes
projectRootNo
maxVariablesNo

TDQS

B3.4/5.0
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 the tool's output nature (compressed summary, sources, risk hotspots) and hints at performance ('load once per session'), suggesting it is a read-only aggregation operation. However, it does not explicitly state whether it modifies state, whether it performs file I/O that might have side effects, or any rate limits. The description is informative but not fully transparent about behavioral boundaries.

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 a single sentence that packs a lot of relevant information: purpose, content, and usage guidance. It front-loads the core purpose ('Compressed, project-wide summary') and then adds specifics. It is concise and well-structured, though it could be slightly less dense. No waste.

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

Completeness2/5

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

Given the absence of annotations, output schema, and parameter descriptions, the description must provide extensive context. It explains what the tool returns and gives a usage hint, but it omits essential details: what files are expected (input semantics), how projectRoot and maxVariables affect behavior, what the output format is, and when to use this versus other siblings beyond resolve_variable. The description is insufficient for an agent to confidently invoke this tool correctly.

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

Parameters1/5

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

Schema description coverage is 0%, meaning the input schema provides no explanations for the three parameters. The description does not mention any of them (files, projectRoot, maxVariables). An agent has no clue from the description what values to provide or how the parameters affect the tool's behavior. The description completely fails to compensate for the schema gap, making parameter semantics severely deficient.

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 specifies the tool's purpose: producing a compressed, project-wide summary of config variables, including sources, domains, and risk hotspots. It explicitly distinguishes itself from sibling resolve_variable by positioning as a session-level alternative, making it unambiguous what the tool does and when it differs from at least one sibling.

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 provides explicit usage guidance: 'Load once per session instead of repeated resolve_variable calls.' This tells an agent when to prefer this tool over a specific sibling. However, it does not mention other siblings (trace_variable, impact_preview, diff_environments) or provide exclusions for when not to use this tool, so it's not fully comprehensive.

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

diff_environmentsA

Resolves every variable under two different environment/service/workload selectors and reports what differs between them.

ParametersJSON Schema
NameRequiredDescriptionDefault
filesYes
variablesNoOptional subset; defaults to every variable discovered
projectRootNo
environmentAYes{ nodeEnv?, service?, workload?, container?, label? }
environmentBYes{ nodeEnv?, service?, workload?, container?, label? }

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are provided, so the description carries the behavioral burden. It conveys that the operation resolves variables and reports differences, implying a read-only comparison. However, it does not disclose output format, possible failure modes, performance implications, or whether any resolution side effects occur.

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 one dense, purposeful sentence with no filler. It front-loads the core verb and resource, states the comparison scope, and communicates the output concept without redundancy.

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

Completeness2/5

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

With five parameters, nested objects, no output schema, and no annotations, this description leaves important gaps: what 'files' represents, what values the selectors may contain, what a 'difference' report looks like, and when this tool is preferable to resolve_variable or trace_variable. The core idea is present, but an agent would struggle to call it correctly without guessing.

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

Parameters2/5

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

Schema coverage is 60%; variables and the two environment objects have descriptions, and the description reinforces that all discovered variables are included by default. However, the required 'files' parameter and 'projectRoot' have no schema descriptions and the description does not clarify their meaning, leaving a critical input unexplained.

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 names a specific action ('Resolves every variable') and a distinct resource ('two different environment/service/workload selectors'), then states the comparison outcome ('reports what differs'). This clearly separates it from siblings like resolve_variable, which handles a single variable, and trace_variable, which traces rather than diffs.

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 phrase 'under two different environment/service/workload selectors' gives clear context for when to invoke this tool: when an agent needs to compare resolved variables across two configurations. It does not explicitly exclude alternatives or name sibling tools, but the intended scenario is apparent.

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

impact_previewB

Predicts which environments/services/workloads are actually affected if a variable's value in one file is changed (or removed) — including which contexts are shielded by a higher-precedence source.

ParametersJSON Schema
NameRequiredDescriptionDefault
fileYesThe file that would be edited
filesYes
newValueNoOmit to simulate removing the assignment entirely
variableYes
projectRootNo

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral burden. It adds one meaningful behavior (higher-precedence shielding) but does not disclose whether the tool is read-only, error behavior (e.g., variable not found), or what the output is (e.g., list of affected items). This is a clear gap, but the precedence detail provides partial transparency.

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 entire description is a single, tight sentence that front-loads the verb 'Predicts' and packs in the core purpose plus a behavioral nuance. There is no redundant phrasing or filler—every word earns its place.

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

Completeness2/5

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

Despite the tool's moderate complexity (impact prediction across environments with precedence), the description omits critical context: it does not explain how parameters like 'files' and 'projectRoot' influence behavior, nor what the return value looks like. An agent would struggle to construct a correct call without additional inference.

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

Parameters2/5

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

Schema coverage is only 40%, so the description must compensate for poorly documented parameters like 'files', 'variable', and 'projectRoot'. It only indirectly references 'file' and 'variable' and does not clarify the purpose of 'files' (plural) or why 'projectRoot' is needed. This fails to add meaning 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 uses a specific verb ('Predicts') and identifies the exact resource (environments/services/workloads affected by a variable change). It also adds a distinguishing nuance about precedence shielding, which differentiates it from siblings like resolve_variable or trace_variable without naming them.

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 states what the tool does but gives no guidance on when to use it versus alternatives. It does not mention conditions, exclusions, or situations where another sibling tool would be more appropriate. This leaves the agent without direction for tool selection.

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

resolve_variableA

Resolves what a config/env variable actually evaluates to across dotenv, docker-compose, and Kubernetes sources, and which source wins.

ParametersJSON Schema
NameRequiredDescriptionDefault
filesYesPaths (relative to projectRoot) to .env*, compose, and k8s manifest files to consider
serviceNodocker-compose service name to resolve for
variableYesThe variable name, e.g. DATABASE_URL
workloadNoKubernetes workload (Deployment/Pod/etc.) name to resolve for
containerNoKubernetes container name within the workload
environmentNoTarget NODE_ENV-style value for dotenv resolution, e.g. "production"
projectRootNoDirectory the file paths are relative to

TDQS

A4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the behavioral burden. It does disclose important behavior: resolution spans dotenv, docker-compose, and Kubernetes, and precedence is evaluated. However, it does not state side-effect freedom, error behavior, missing-file handling, or any operational prerequisites, leaving notable gaps for a tool with no annotation support.

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?

One concise, front-loaded sentence delivers the core function and the key differentiator (which source wins). There is no filler or redundant restatement of the tool name.

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 the moderate complexity of 7 parameters, full schema coverage, and no output schema, the description is largely sufficient: it states what the tool returns conceptually (evaluated value and winning source) and all parameters are otherwise documented. It could be stronger by noting how to handle missing variables or by connecting to sibling tools, but the essential selection and invocation context is present.

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 every parameter. The description adds conceptual context by naming the source types, which loosely ties to files/service/workload/container, but it does not add parameter-level detail beyond what the schema provides, so the baseline of 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?

Description uses a specific verb ('resolves') and identifies the exact resource: what a config/env variable evaluates to across dotenv, docker-compose, and Kubernetes, including which source wins. This clearly differentiates it from siblings by focusing on multi-source resolution and precedence, not tracing, manifest inspection, impact, or diffing.

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 implies a clear usage context: use when you need the actual evaluated value of a variable across multiple config-source types and the winning source. It does not explicitly name alternatives or state when not to use it, so it stops short of the strongest guidance.

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

trace_variableA

Lists every place a variable is defined or read across dotenv, compose, k8s, and code, and what wins in each discovered environment/service/workload context.

ParametersJSON Schema
NameRequiredDescriptionDefault
filesYes
variableYes
projectRootNo

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the burden, and it does a solid job: it reveals that the tool is a read/analysis operation that returns locations and precedence outcomes. It does not discuss edge cases or failure modes, but it clearly communicates the core observable behavior and that it is non-mutating.

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 entire description is one dense, front-loaded sentence with no filler. Every clause contributes meaning: what is listed, where it is searched, and what result is produced.

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

Completeness2/5

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

The core purpose is clear, but the definition is incomplete for reliable invocation: there is no output schema, no annotations, no guidance on files/projectRoot semantics, and no differentiation from sibling tools. An agent would likely need to inspect the schema or guess to use it correctly.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must explain parameters. It clarifies that 'variable' is the trace target, but it gives no meaning for 'files' or 'projectRoot'—what files should contain, whether they are required, or how projectRoot changes discovery. This is a significant gap for a schema with no inline 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?

The description uses a specific verb ('Lists'), names the resource (variable definitions/reads), and defines scope across dotenv, compose, k8s, and code. It also conveys a distinct deliverable ('what wins in each discovered environment/service/workload context'), which separates it from siblings like resolve_variable or diff_environments.

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 usage context is implied rather than explicit: an agent can infer this is the tool to use when all definition/read locations and precedence are needed. However, it never states when not to use it or names alternative tools, leaving the agent to reason from sibling names.

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

A3.7/5.0
Disambiguation4/5

Most tools are clearly separated by purpose: manifest summarizes, impact previews, diff compares, and trace enumerates. The only real overlap is between resolve_variable and trace_variable, since both explain precedence and 'what wins,' though one targets the final value and the other targets all definition/read locations.

Naming Consistency3/5

resolve_variable and trace_variable follow a clean verb_noun pattern, but config_manifest and impact_preview are noun compounds, and diff_environments uses a terse verb. The names are readable and descriptive, but the naming convention is not uniform across the set.

Tool Count5/5

Five tools is well-scoped for a read-only environment/config analysis server. Each tool covers a distinct analytical need without redundancy or bloat, and the count feels intentional rather than thin or excessive.

Completeness5/5

The set covers the full analysis workflow: resolving a single variable, tracing all usages, generating a project-wide manifest, predicting change impact, and diffing environments. No obvious missing operation is needed for the stated domain.

Maintenance

ActivityMaintained
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

  • onboard-mcp

    developerpankajdixit
    A
    license
    A
    quality
    A
    maintenance
    Checks your local development environment for common issues like wrong Node version, missing Docker, missing git config, missing .env keys, and busy ports, and provides fixes.
    6
    17
    1
    MIT

  • devenv-doctor-mcp

    Madiocre
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables LLM clients to inspect local dev environments—Docker container health, pnpm workspace integrity, and stuck process detection—without manual terminal copy-pasting.
    MIT

  • DevTwin MCP

    JaydeepDhamecha
    A
    license
    A
    quality
    B
    maintenance
    Provides AI coding agents with structured, evidence-based diagnostics about the local development environment, detecting tech stack, runtime mismatches, dependency state, services, ports, and Git status without exposing secrets or using network calls.
    10
    Apache 2.0

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/Patrizzos/EnvSpeak'

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