coding-agent-mcp (spyduck007/agent-mcp) is an MCP server listed on the M8ven Trust Index. It scores 52 out of 100, grade D. It declares 68 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
52/100

coding-agent-mcp

Containerized MCP server for coding agents with tools for file editing, shell commands, process management, Git, browser automation, and project snapshots.

→ spyduck007/agent-mcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

spyduck007

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// tools this server exposes68 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

open_project

Open a project directory and make it the active project.

switch_project

Switch to a previously opened project.

list_projects

List opened projects.

close_project

Forget an opened project.

pwd

Return the active project directory.

write_file
append_file
read_file
read_files
replace_in_file
replace_lines
insert_at_line
copy_path
move_path
delete_path
create_directory
list_files
tree
find_file
search_files
regex_search
find_symbol
stat_path
run_command
command_history
start_process

Start a long-running process and capture output in the background without blocking.

list_processes

List tracked background processes.

get_process_output

Return captured process output without blocking. Use since_line for incremental reads.

wait_for_process_output

Wait until text appears in background process output, without blocking forever.

stop_process

Stop a tracked process. Uses terminate first unless kill=True.

forget_process

Remove a stopped process from the tracked process list.

apply_patch
git_status
git_diff
git_log
git_branch
git_checkout
git_commit
git_restore
fetch_url
browser_inspect

Inspect a page: title, final URL, headings, links, buttons, inputs, and visible body text.

browser_check_errors

Open a page and collect console errors, page exceptions, failed requests, and non-2xx/3xx responses.

browser_interact

Run browser actions from a fresh page and return a text DOM summary. Locators can use selector, role/name, text, label, placeholder, test_id, alt_text, or title. Supported actions: click, dblclick, fill, type, press, hover, check, uncheck, select, focus, blur, wait_for_selector, wait_for_text, wait_…

browser_evaluate

Evaluate JavaScript on a page and return the JSON-serializable result.

browser_dom_snapshot

Return a structured, text-only DOM snapshot focused on useful/interactive elements. No screenshots or images.

browser_accessibility_snapshot

Return a text-only accessibility-oriented snapshot: roles, names, fields, headings, links, landmarks, and controls.

browser_form_snapshot

Return form/action/field metadata for a page, including labels, names, placeholders, values, required and disabled flags.

browser_assert

Run optional actions and assertion actions against a fresh page. Assertion actions include assert_text, assert_selector, assert_count, assert_url, and assert_title.

browser_network_trace

Open a page, optionally run actions, and return request/response/failure/console traces as text JSON.

browser_storage_state

Return cookies, localStorage, and sessionStorage for a page after navigation.

browser_session_open

Open a persistent browser session for multi-step testing across MCP calls. Close it with browser_session_close.

browser_session_list

List open persistent browser sessions.

browser_session_close

Close a persistent browser session and free its browser process.

browser_session_inspect

Inspect the current page in a persistent browser session.

browser_session_interact

Run actions in an existing persistent browser session and return the updated text DOM summary.

browser_session_evaluate

Evaluate JavaScript in an existing persistent browser session.

browser_session_dom_snapshot

Return a structured DOM snapshot for the current page in a persistent browser session.

browser_session_accessibility_snapshot

Return an accessibility-oriented snapshot for the current page in a persistent browser session.

browser_session_logs

Return recent console errors/warnings, page errors, failed requests, and bad responses for a persistent browser session.

create_snapshot
restore_snapshot
list_snapshots
get_project_info
environment_info
install_apt_packages

Install Debian packages inside the MCP container.

install_python_packages

Install Python packages globally inside the MCP container.

install_node_packages

Install Node packages in the active project.

install_project_dependencies

Install dependencies for the active project.

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

68/68 tools missing one or more hints — open_project (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); switch_project (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_projects (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +65 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

2 tools perform destructive updates without destructiveHint — delete_path deletes at line 298 (shutil.rmtree(target)); restore_snapshot deletes at line 1756 (shutil.rmtree(item))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool inputs are validated

61/68 tool handlers declare input schemas (90%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 16/68 tool handlers wrap calls in try/catch (24%)

Wrap each tool handler body in try/catch and return a structured error response.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/spyduck007/agent-mcp?variant=verified)](https://m8ven.ai/mcp/spyduck007/agent-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 37eaddabb2c4222eb2e22421c1ec468873a2e51c
code hash: c6bf632f51ccfee2a2d7b71e99543d898499e3c84b8a9323a88e307c80e77bb7
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client