Skip to main content
Glama
ajipurn

Fida

by ajipurn
OverviewSchemaRelated ServersScoreDiscussions
Rust
Local

Keep secret values out of AI coding agents.

Fida is a local-first secret leak prevention layer for AI coding agents. It finds exposed credentials, gives agents redacted safe views of sensitive files and command output, and shows whether your installed agent integrations can still expose a raw value.

It is deliberately not a general agent policy engine, approval system, or developer workflow firewall. Fida does not decide which ordinary commands an agent may run, which files it may edit, or whether you may use curl | sh. Its one job is simple: a detected secret must not reach model context.

Project status: MVP implemented. Fida installs local integrations, verifies its redaction path with a synthetic credential, scans repo risk, and records redaction-safe audit events.

Quick start

# Install the binary. In a terminal it offers to set up protection right away.
curl -fsSL https://raw.githubusercontent.com/ajipurn/fida/main/install.sh | sh

# Run fida with no arguments any time to set up — or, once installed, to update.
fida

# Check coverage, including how many secrets have been protected.
fida status

fida is install-and-forget: it wires every coding agent it detects, and running it again later checks for an update. Run from a terminal, the installer offers to do this for you; piped or in CI it stays quiet and just prints fida as the next step.

Related MCP server: ContextLock

What Fida does

When an agent needs content that may contain a credential, Fida provides a sanitized view instead of the raw bytes:

Agent -> fida_read .env -> scan -> redact -> agent

API_URL=https://example.test
API_KEY=[REDACTED]

Its integrations combine three layers:

  1. Redacting MCP gateway — fida_read and fida_shell return redacted file content and captured command output. fida_shell still runs the real command — the child process keeps the true credential, so the work succeeds — and redacts only the output handed back to the model: the agent uses a secret without seeing it. File reads are confined to the workspace by default, with optional explicit read roots for trusted user attachments; secrets outside those roots (e.g. ~/.aws) are covered only by the native-read hook on enforced agents.

  2. Agent steering — a managed instruction tells the agent to use those redacting tools whenever it needs sensitive content.

  3. Native-read hook, where supported — Codex and Claude Code can block a native read only when Fida detects secret content that the native tool cannot redact, then direct the agent to the gateway.

Normal clean reads, edits, commands, installs, network access, and approvals remain the agent's and developer's concern. Fida's gateway follows the same low-friction rule: it captures and redacts output; it does not apply a command allowlist or repository approval policy.

What Fida detects

The built-in detector catalog recognizes dotenv assignments, PEM private keys, and high-precision formats for AWS, GitHub, Google, Slack, Stripe, OpenAI, Anthropic, and JWT credentials. It favors precision over recall: a credential in a format Fida does not recognize passes through unredacted. This is best-effort protection against accidental exposure, not a guarantee of zero leakage. Use a dedicated history scanner such as gitleaks or GitGuardian alongside Fida.

Fida fails closed on redaction: if it cannot prove a response is clean, it suppresses that response rather than returning a partial secret.

Install

curl -fsSL https://raw.githubusercontent.com/ajipurn/fida/main/install.sh | sh

The binary is installed to ~/.local/bin by default. Run in an interactive terminal, the installer then offers to wire protection for you; otherwise start setup yourself:

fida

Pin a version or choose another install directory:

FIDA_VERSION=v0.1.0 FIDA_INSTALL_DIR=/usr/local/bin \
  curl -fsSL https://raw.githubusercontent.com/ajipurn/fida/main/install.sh | sh

Other options:

cargo install --git https://github.com/ajipurn/fida fida-cli

git clone https://github.com/ajipurn/fida
cd fida
./install.sh

Everyday commands

fida                  # protect every detected agent (or, once installed, update)
fida on [agent]       # protect one agent, or all detected agents
fida off [agent]      # remove protection from one agent, or all of them
fida status           # coverage + how many secrets have been protected
fida scan             # find secret risk without printing secret values
fida scan --fail-on high

fida scan reports whether a raw secret could reach a detected agent. It never prints a secret value, its length, or a fragment of it.

Agent coverage

Agent

Coverage

Codex, Claude Code

enforced when the hook and gateway self-test pass

Cursor, OpenCode, GitHub Copilot, Windsurf, Antigravity, Kiro

best_effort gateway + steering

fida status reports the actual state for each detected agent: enforced, best_effort, incomplete, or inactive.

Scope and limits

Fida protects model-bound content on its installed integration paths. It is not an OS sandbox or a complete data-loss-prevention product. An agent that can ignore steering, bypass a hook, or access a file through an unmediated native tool may still need OS-level containment. Fida names that coverage honestly instead of turning ordinary development into a permission maze.

Development

cargo fmt --all --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace

Security

Please report security-sensitive issues privately when they could expose a secret, bypass redaction, or misrepresent protection coverage. See SECURITY.md.

License

Licensed under the terms in LICENSE.

Available Tools

2 tools
fida_readA

Read a file's text through Fida policy (files.read). Use this for every file read, ahead of native reads, workspace context, reviewed-file context, lean-ctx/ctx_read, or other MCP file tools, so policy can block denied paths and secret values in returned content are redacted.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYesFile path, relative to the workspace or absolute.

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 two key behaviors: policy can block denied paths and secret values are redacted. This adds significant value beyond a simple read. Lacks details on return format or error handling, but acceptable for a simple 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?

Two sentences with no wasted words. First sentence states purpose, second provides usage guidance. Efficient and front-loaded.

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 simplicity (single parameter, no output schema), the description covers purpose, usage, and behavioral traits. It mentions policy enforcement and redaction, which is contextual. Could be slightly more explicit about return type, but overall complete.

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% with a description for the 'path' parameter. The tool description does not add additional parameter-specific meaning beyond what the schema provides, so 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?

The description clearly states it reads a file's text through Fida policy. It specifies the verb 'read' and resource 'file's text', and distinguishes it from sibling 'fida_shell' by indicating it is for file reads only.

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 says to use this tool for every file read ahead of native reads, workspace context, reviewed-file context, and other MCP file tools. Provides clear context on when to use and lists alternatives.

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

fida_shellA

Run a command through Fida policy (commands.run). Use this instead of native shell execution or non-Fida MCP shell tools so the policy can gate the command. Stdout/stderr are returned with secrets redacted.

ParametersJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory; defaults to the workspace root.
commandYesCommand line; split on whitespace into argv.

TDQS

A4.2/5.0
Behavior3/5

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

No annotations provided, so description must disclose behaviors. It reveals that stdout/stderr are returned with secrets redacted, which is useful. However, it omits other important behaviors like error handling, exit codes, policy blocking details, or permission requirements. The description adds some value but is not comprehensive.

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?

Three concise sentences with no wasted words. The first sentence states the core function, the second provides usage guidance, and the third describes output. Information is front-loaded and efficiently structured.

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 simple tool with only two parameters and no output schema, the description covers the main purpose, usage context, and return format (stdout/stderr with redacted secrets). It is missing details on error behavior and exit codes, but these are less critical. Overall, it provides sufficient context for an agent to use the tool effectively.

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 explains both parameters (command and cwd). The description does not add any additional semantic information about the parameters beyond what the schema provides, so 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?

Description clearly states the tool runs a command through Fida policy and distinguishes it from native shell or non-Fida MCP tools. The verb 'run' and resource 'command through Fida policy' are specific, and it differentiates from the sibling fida_read.

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 tells when to use this tool (instead of native shell or non-Fida MCP shell tools) and why (so policy can gate the command). Provides clear guidance on alternatives.

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. 2 tool updatesv0.1.6
    • First observedfida_read
    • First observedfida_shell
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.1/5.0
Disambiguation5/5

The two tools have clearly distinct purposes: fida_read handles file reads, fida_shell handles command execution. There is no overlap in functionality.

Naming Consistency5/5

Both tools follow a consistent pattern: 'fida_' prefix + verb (read, shell). This is a predictable and uniform naming convention.

Tool Count3/5

With only 2 tools, the server is very minimal. While it may cover essential file read and shell execution, it feels thin for a security policy tool that could include more operations.

Completeness2/5

The server lacks write, delete, or policy management tools. For a policy-enforcing tool, there are notable gaps such as file writes or policy listing, which would be expected.

Maintenance

ActivityStale
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

  • ContextLock

    LutaElbert
    A
    license
    Not graded
    quality
    A
    maintenance
    A local-first MCP safety layer that blocks dangerous files and redacts secrets before AI agents can access them, ensuring safe vibe coding.
    13
    Apache 2.0

  • DevVault MCP

    ConjureGanja
    F
    license
    A
    quality
    C
    maintenance
    A local-first secrets vault for MCP clients that lets AI assistants use secrets by injecting them into child processes, without the plaintext ever entering the model's context.
    5
    -

  • credential-broker-mcp

    SarutobiSasuke8
    A
    license
    Not graded
    quality
    B
    maintenance
    A local-first MCP server that lets AI agents use gated APIs without holding keys, enforcing declarative policies, injecting secrets server-side, and auditing access without content.
    2
    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/ajipurn/fida'

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