A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Exarp is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
2
downloads in 30d
local
runs on your machine
53
tools declared
What it does
MCP server for project management automation - health scores, task alignment, security scanning
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user exarp-mcp '--' uvx --with 'mcp<2' exarp
# 2 — ask your agent for something these tools do
# add_external_tool_hints, tool_catalog, workflow_mode and 50 more
Exarp costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DAAll 1 server
davidl711 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Exarp as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user exarp-mcp '--' uvx --with 'mcp<2' exarpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
53 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
[HINT: Tool hints. Files scanned, modified, hints added.]
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Get the current status of the project management automation server.
No parameter schema on file.
[HINT: Report generation. action=overview|scorecard|briefing|prd. Project reports.]
No parameter schema on file.
[HINT: Task workflow. action=sync|approve|clarify|clarity|cleanup. Manage task lifecycle.]
No parameter schema on file.
[HINT: Memory maintenance. action=health|gc|prune|consolidate|dream. Lifecycle management.]
No parameter schema on file.
[HINT: Automation. action=daily|nightly|sprint|discover. Unified automation tool.]
No parameter schema on file.
[HINT: Ollama. action=status|models|generate|pull|hardware|docs|quality|summary. Unified Ollama tool.]
No parameter schema on file.
[HINT: Git tools. action=commits|branches|tasks|diff|graph|merge|set_branch. Unified git-inspired tools.]
No parameter schema on file.
[HINT: Session. action=prime|handoff|prompts|assignee. Unified session management tools.]
No parameter schema on file.
Generate comprehensive documentation for Python code using CodeLlama.
No parameter schema on file.
Analyze Python code quality using CodeLlama.
No parameter schema on file.
Use CodeLlama to create intelligent summaries of tool outputs.
No parameter schema on file.
Check if Ollama server is running and accessible.
No parameter schema on file.
Get hardware information and recommended Ollama performance settings.
No parameter schema on file.
List all available Ollama models on the local server.
No parameter schema on file.
No parameter schema on file.
Download/pull an Ollama model from the registry.
No parameter schema on file.
No parameter schema on file.
[HINT: Auto-primer. Returns optimal context for session start. Detects agent/time/mode.]
No parameter schema on file.
[HINT: Task context. Get optimized context for working on a task.]
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Exarp or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.2.2 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings13 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest0d3d16329ff004deeab84ebcaa9d36e182d6fac274b0e08c1db0d32203643724
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (49 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
6 of the 49 recovered tools are registered only when TOOLS_AVAILABLE holds (project_management_automation/server.py:1871) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
16 of the 49 recovered tools are registered only when CONSOLIDATED_AVAILABLE holds (project_management_automation/server.py:2310) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
8 of the 49 recovered tools are registered only when GIT_INSPIRED_TOOLS_AVAILABLE holds (project_management_automation/server.py:2944) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
4 of the 49 recovered tools are registered only when not MLX_AVAILABLE is false (project_management_automation/tools/mlx_integration.py:489) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
3 of the 49 recovered tools are registered only when not OLLAMA_AVAILABLE is false (project_management_automation/tools/ollama_enhanced_tools.py:357) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
5 of the 49 recovered tools are registered only when not OLLAMA_AVAILABLE is false (project_management_automation/tools/ollama_integration.py:908) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
7 tools are registered unconditionally · (1) 6 more only when TOOLS_AVAILABLE holds (project_management_automation/server.py:1871) · (2) 16 more only when CONSOLIDATED_AVAILABLE holds (project_management_automation/server.py:2310) · (3) 8 more only when GIT_INSPIRED_TOOLS_AVAILABLE holds (project_management_automation/server.py:2944) · (4) 4 more only when not MLX_AVAILABLE is false (project_management_automation/tools/mlx_integration.py:489) · (5) 3 more only when not OLLAMA_AVAILABLE is false (project_management_automation/tools/ollama_enhanced_tools.py:357) · (6) 5 more only when not OLLAMA_AVAILABLE is false (project_management_automation/tools/ollama_integration.py:908) — typically when a key or option is configured. All 49 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| find_prompts | no tags | |
| infer_session_mode | no tags | |
| add_external_tool_hints conditional (1) | no tags | |
| automation conditional (1) | external-sink | external-sink: keyword "send_notification" |
| tool_catalog conditional (1) | no tags | |
| workflow_mode conditional (1) | external-sink | external-sink: keyword "send_notification" |
| context conditional (1) | no tags | |
| recommend conditional (1) | no tags | |
| analyze_alignment conditional (2) | no tags | |
| security conditional (2) | untrusted-input | untrusted-input: keyword "fetch" |
| generate_config conditional (2) | no tags | |
| setup_hooks conditional (2) | no tags | |
| prompt_tracking conditional (2) | no tags | |
| health conditional (2) | no tags | |
| check_attribution conditional (2) | no tags | |
| task_analysis conditional (2) | no tags | |
| testing conditional (2) | no tags | |
| lint conditional (2) | no tags | |
| memory conditional (2) | no tags | |
| task_discovery conditional (2) | no tags | |
| task_workflow conditional (2) | no tags | |
| estimation conditional (2) | no tags | |
| memory_maint conditional (2) | no tags | |
| get_task_commits_tool conditional (3) | no tags | |
| get_branch_commits_tool conditional (3) | no tags | |
| list_branches_tool conditional (3) | no tags | |
| get_branch_tasks_tool conditional (3) | no tags | |
| compare_task_diff_tool conditional (3) | no tags | |
| generate_graph_tool conditional (3) | no tags | |
| merge_branch_tools_tool conditional (3) | no tags | |
| set_task_branch conditional (3) | no tags | |
| server_status | no tags | |
| report conditional (2) | no tags | |
| auto_prime_session | no tags | |
| get_task_context | no tags | |
| check_mlx_status_tool conditional (4) | no tags | |
| get_mlx_hardware_info_tool conditional (4) | no tags | |
| list_mlx_models_tool conditional (4) | untrusted-input | untrusted-input: keyword "download" |
| generate_with_mlx_tool conditional (4) | no tags | |
| generate_code_documentation_tool conditional (5) | no tags | |
| analyze_code_quality_tool conditional (5) | no tags | |
| enhance_context_summary_tool conditional (5) | no tags | |
| check_ollama_status_tool conditional (6) | no tags | |
| get_hardware_info_tool conditional (6) | no tags | |
| list_ollama_models_tool conditional (6) | no tags | |
| generate_with_ollama_tool conditional (6) | no tags | |
| pull_ollama_model_tool conditional (6) | untrusted-input | untrusted-input: keyword "download" |
| exarp_session_handoff | no tags | |
| task_assignee_tool | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest0d3d16329ff004de
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.2.2. Pin a release below and the command asks for exactly that one.
0.2.2
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Exarp can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.